Documentation 2026-05-27 00:57 UTC to 2026-05-28 18:58 UTC

53| `cli_auth_credentials_store` | `file | keyring | auto` | Control where the CLI stores cached credentials (file-based auth.json vs OS keychain). |53| `cli_auth_credentials_store` | `file | keyring | auto` | Control where the CLI stores cached credentials (file-based auth.json vs OS keychain). |

54| `commit_attribution` | `string` | Commit co-author trailer used when `[features].codex_git_commit` is enabled. Defaults to `Codex <noreply@openai.com>`; set `""` to disable. |54| `commit_attribution` | `string` | Commit co-author trailer used when `[features].codex_git_commit` is enabled. Defaults to `Codex <noreply@openai.com>`; set `""` to disable. |

55| `compact_prompt` | `string` | Inline override for the history compaction prompt. |55| `compact_prompt` | `string` | Inline override for the history compaction prompt. |

56| `default_permissions` | `string` | Name of the default permissions profile to apply to sandboxed tool calls. Built-ins are `:read-only`, `:workspace`, and `:danger-full-access`; custom profile names require matching `[permissions.<name>]` tables. |56| `default_permissions` | `string` | Name of the default permissions profile to apply to sandboxed tool calls. Built-ins are `:read-only`, `:workspace`, and `:danger-full-access`; custom profile names require matching `[permissions.<name>]` tables. Don't combine with `sandbox_mode` or `[sandbox_workspace_write]`. |

57| `developer_instructions` | `string` | Additional developer instructions injected into the session (optional). |57| `developer_instructions` | `string` | Additional developer instructions injected into the session (optional). |

58| `disable_paste_burst` | `boolean` | Disable burst-paste detection in the TUI. |58| `disable_paste_burst` | `boolean` | Disable burst-paste detection in the TUI. |

59| `experimental_compact_prompt_file` | `string (path)` | Load the compaction prompt override from a file (experimental). |59| `experimental_compact_prompt_file` | `string (path)` | Load the compaction prompt override from a file (experimental). |

194| `otel.trace_exporter.<id>.tls.ca-certificate` | `string` | CA certificate path for OTEL trace exporter TLS. |194| `otel.trace_exporter.<id>.tls.ca-certificate` | `string` | CA certificate path for OTEL trace exporter TLS. |

195| `otel.trace_exporter.<id>.tls.client-certificate` | `string` | Client certificate path for OTEL trace exporter TLS. |195| `otel.trace_exporter.<id>.tls.client-certificate` | `string` | Client certificate path for OTEL trace exporter TLS. |

196| `otel.trace_exporter.<id>.tls.client-private-key` | `string` | Client private key path for OTEL trace exporter TLS. |196| `otel.trace_exporter.<id>.tls.client-private-key` | `string` | Client private key path for OTEL trace exporter TLS. |

197| `permissions.<name>.description` | `string` | Human-readable description for this named profile. A profile does not inherit its parent's description through `extends`. |

198| `permissions.<name>.extends` | `string` | Optional parent profile applied before this named profile. Set it to another named profile, `:read-only`, or `:workspace`; `:danger-full-access`, undefined parents, and cycles are rejected. |

197| `permissions.<name>.filesystem` | `table` | Named filesystem permission profile. Each key is an absolute path or special token such as `:minimal` or `:workspace_roots`. |199| `permissions.<name>.filesystem` | `table` | Named filesystem permission profile. Each key is an absolute path or special token such as `:minimal` or `:workspace_roots`. |

198| `permissions.<name>.filesystem.":workspace_roots".<subpath-or-glob>` | `"read" | "write" | "deny"` | Scoped filesystem access relative to each effective workspace root. Use `"."` for the root itself; glob subpaths such as `"**/*.env"` can deny reads with `"deny"`. |200| `permissions.<name>.filesystem.":workspace_roots".<subpath-or-glob>` | `"read" | "write" | "deny"` | Scoped filesystem access relative to each effective workspace root. Use `"."` for the root itself; glob subpaths such as `"**/*.env"` can deny reads with `"deny"`. |

199| `permissions.<name>.filesystem.<path-or-glob>` | `"read" | "write" | "deny" | table` | Grant direct access for a path, glob pattern, or special token, or scope nested entries under that root. Use `"deny"` to deny reads for matching paths. |201| `permissions.<name>.filesystem.<path-or-glob>` | `"read" | "write" | "deny" | table` | Grant direct access for a path, glob pattern, or special token, or scope nested entries under that root. Use `"deny"` to deny reads for matching paths. |

663 665 

664Details666Details

665 667 

666Name of the default permissions profile to apply to sandboxed tool calls. Built-ins are `:read-only`, `:workspace`, and `:danger-full-access`; custom profile names require matching `[permissions.<name>]` tables.668Name of the default permissions profile to apply to sandboxed tool calls. Built-ins are `:read-only`, `:workspace`, and `:danger-full-access`; custom profile names require matching `[permissions.<name>]` tables. Don't combine with `sandbox_mode` or `[sandbox_workspace_write]`.

667 669 

668Key670Key

669 671 

2347 2349 

2348Key2350Key

2349 2351 

2352`permissions.<name>.description`

2353 

2354Type / Values

2355 

2356`string`

2357 

2358Details

2359 

2360Human-readable description for this named profile. A profile does not inherit its parent's description through `extends`.

2361 

2362Key

2363 

2364`permissions.<name>.extends`

2365 

2366Type / Values

2367 

2368`string`

2369 

2370Details

2371 

2372Optional parent profile applied before this named profile. Set it to another named profile, `:read-only`, or `:workspace`; `:danger-full-access`, undefined parents, and cycles are rejected.

2373 

2374Key

2375 

2350`permissions.<name>.filesystem`2376`permissions.<name>.filesystem`

2351 2377 

2352Type / Values2378Type / Values

108path is readable or writable. For example, a profile can make workspace roots108path is readable or writable. For example, a profile can make workspace roots

109writable while still setting a matching `.env` path to `deny`.109writable while still setting a matching `.env` path to `deny`.

110 110 

111## Extend a profile

112 

113Use `extends` when a profile is mostly the same as a built-in or another named

114profile. Prefer extending a built-in profile over starting from scratch so

115baseline protections carry forward. Extending `:workspace`, for example, keeps

116the workspace root’s `.codex` directory read-only unless you explicitly

117override it. Set the parent once, then add or override only the rules that

118differ.

119 

120```

121default_permissions = "project-edit"

122 

123[permissions.project-edit]

124description = "Project editing with OpenAI API access."

125extends = ":workspace"

126 

127[permissions.project-edit.filesystem.":workspace_roots"]

128"**/*.env" = "deny"

129 

130[permissions.project-edit.network]

131enabled = true

132 

133[permissions.project-edit.network.domains]

134"api.openai.com" = "allow"

135```

136 

137This profile starts with `:workspace`, keeps matching `.env` files denied, and

138allows requests to `api.openai.com`. A profile can extend `:read-only`,

139`:workspace`, or another named profile. It cannot extend

140`:danger-full-access`; Codex also rejects unknown parents and inheritance

141cycles.

142 

111## Configuration spec143## Configuration spec

112 144 

113| Entry | Type / values | Default | Details |145| Entry | Type / values | Default | Details |

114| --- | --- | --- | --- |146| --- | --- | --- | --- |

115| `default_permissions` | String profile name | None | Names the permissions profile Codex applies by default. The value must match a profile under `[permissions]` or a built-in profile such as `:workspace`. Required when permission profiles are active. If an older sandbox setting is active, Codex uses those older sandbox settings instead. |147| `default_permissions` | String profile name | None | Names the permissions profile Codex applies by default. The value must match a profile under `[permissions]` or a built-in profile such as `:workspace`. Required when permission profiles are active. If an older sandbox setting is active, Codex uses those older sandbox settings instead. |

116| `[permissions.<name>]` | Table | None | Defines a profile and its identifier. `default_permissions` selects one profile as the default; other permission-profile selectors also use the profile name. |148| `[permissions.<name>]` | Table | None | Defines a profile and its identifier. `default_permissions` selects one profile as the default; other permission-profile selectors also use the profile name. |

149| `permissions.<name>.description` | String | None | Provides a human-readable description for the profile. A profile does not inherit its parent’s description through `extends`. |

150| `permissions.<name>.extends` | String profile name | None | Starts this profile from another named profile or the built-in `:read-only` or `:workspace` profile. Codex rejects `:danger-full-access`, unknown parents, and inheritance cycles. |

117| `[permissions.<name>.workspace_roots]` | Table | None | Adds profile-defined workspace roots that receive `:workspace_roots` filesystem rules alongside the current session’s runtime workspace roots. |151| `[permissions.<name>.workspace_roots]` | Table | None | Adds profile-defined workspace roots that receive `:workspace_roots` filesystem rules alongside the current session’s runtime workspace roots. |

118| `permissions.<name>.workspace_roots."<path>"` | Boolean | `false` | Adds the path to the profile’s workspace root set when `true`. Entries set to `false` remain inactive. |152| `permissions.<name>.workspace_roots."<path>"` | Boolean | `false` | Adds the path to the profile’s workspace root set when `true`. Entries set to `false` remain inactive. |

119| `[permissions.<name>.filesystem]` | Table | None | Maps filesystem paths to access values or scoped subpath maps. Missing or empty filesystem tables keep filesystem access restricted and emit a startup warning. |153| `[permissions.<name>.filesystem]` | Table | None | Maps filesystem paths to access values or scoped subpath maps. Missing or empty filesystem tables keep filesystem access restricted and emit a startup warning. |

7 7 

8Extend what Codex can do, for example:8Extend what Codex can do, for example:

9 9 

10- Install the Codex Security plugin to scan authorized code and confirm

11 plausible vulnerability findings.

10- Install the Gmail plugin to let Codex read and manage Gmail.12- Install the Gmail plugin to let Codex read and manage Gmail.

11- Install the Google Drive plugin to work across Drive, Docs, Sheets, and13- Install the Google Drive plugin to work across Drive, Docs, Sheets, and

12 Slides.14 Slides.

128manual marketplace setup, workspace sharing, plugin manifests, and packaging130manual marketplace setup, workspace sharing, plugin manifests, and packaging

129guidance.131guidance.

130 132 

133## Plugin guides

134 

135- [Codex Security plugin](https://developers.openai.com/codex/security/plugin): Scan authorized code,

136 confirm findings, and prepare reviewed fixes.

137 

1# Security – Codex1# Security – Codex

2 2 

3Codex Security helps engineering and security teams find, validate, and remediate likely vulnerabilities in connected GitHub repositories.3[Install plugin in Codex App](https://chatgpt.com/plugins/share/676aca3811d54fa7bcdef5255236b3c4)

4 4 

5This page covers Codex Security, the product that scans connected GitHub5For installation steps, supported skills, and review boundaries, see the

6repositories for likely security issues. For Codex sandboxing, approvals,6[Codex Security plugin guide](https://developers.openai.com/codex/security/plugin).

7 

8### Explore plugin use cases

9 

10- [Run a deep security scan](https://developers.openai.com/codex/use-cases/deep-security-scan) to perform a higher-recall repository-wide audit.

11- [Scan code changes for security](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security) before you merge a pull request or branch.

12- [Remediate a vulnerability backlog](https://developers.openai.com/codex/use-cases/remediate-vulnerability-backlog) with bounded fixes for approved findings.

13 

14The plugin runs in your Codex thread. Codex Security cloud scans connected

15GitHub repositories through Codex Web. For Codex sandboxing, approvals,

7network controls, and admin settings, see [Agent approvals &16network controls, and admin settings, see [Agent approvals &

8security](https://developers.openai.com/codex/agent-approvals-security).17security](https://developers.openai.com/codex/agent-approvals-security).

9 18 

19## Codex Security cloud

20 

21Codex Security cloud is currently in research preview. It scans connected

22GitHub repositories for likely security issues.

23 

10It helps teams:24It helps teams:

11 25 

121. **Find likely vulnerabilities** by using a repo-specific threat model and real code context.261. **Find likely vulnerabilities** by using a repo-specific threat model and real code context.

132. **Reduce noise** by validating findings before you review them.272. **Reduce noise** by validating findings before you review them.

143. **Move findings toward fixes** with ranked results, evidence, and suggested patch options.283. **Move findings toward fixes** with ranked results, evidence, and suggested patch options.

15 29 

16## How it works30## How Codex Security cloud works

17 31 

18Codex Security scans connected repositories commit by commit.32Codex Security scans connected repositories commit by commit.

19It builds scan context from your repo, checks likely vulnerabilities against that context, and validates high-signal issues in an isolated environment before surfacing them.33It builds scan context from your repo, checks likely vulnerabilities against that context, and validates high-signal issues in an isolated environment before surfacing them.

24- validation evidence that helps reduce false positives38- validation evidence that helps reduce false positives

25- suggested fixes you can review in GitHub39- suggested fixes you can review in GitHub

26 40 

27## Access and prerequisites41## Codex Security cloud access and prerequisites

28 42 

29Codex Security works with connected GitHub repositories through Codex Web. OpenAI manages access. If you need access or a repository isn’t visible, contact your OpenAI account team and confirm the repository is available through your Codex Web workspace.43Codex Security is available for ChatGPT Enterprise, Edu, Business, and Pro users. It works with connected GitHub repositories through Codex Web. If you need access or a repository isn’t visible, confirm the repository is available through your Codex Web workspace or contact your OpenAI account team.

30 44 

31## Related docs45## Related docs

32 46 

33- [Codex Security setup](https://developers.openai.com/codex/security/setup) covers setup, scanning, and findings review.47- [Codex Security plugin guide](https://developers.openai.com/codex/security/plugin) covers local repository and diff-review workflows in Codex.

34- [FAQ](https://developers.openai.com/codex/security/faq) covers common product questions.48- [Codex Security cloud setup](https://developers.openai.com/codex/security/setup) covers setup, scanning, and findings review.

35- [Improving the threat model](https://developers.openai.com/codex/security/threat-model) explains how to tune scope, attack surface, and criticality assumptions.49- [Improving the threat model](https://developers.openai.com/codex/security/threat-model) explains how to tune scope, attack surface, and criticality assumptions.

50- [FAQ](https://developers.openai.com/codex/security/faq) covers common product questions.

36 51 

1# Plugin – Codex Security

2 

3The Codex Security plugin adds security-review workflows to Codex for code that

4you have authorization to assess. Use it from an open repository to investigate

5a codebase, review a change set for security regressions, confirm plausible

6findings, and prepare minimal fixes for review.

7 

8This page covers the installable plugin that runs in your Codex thread. For

9the research-preview product that scans connected GitHub repositories through

10Codex Web, see [Codex Security](https://developers.openai.com/codex/security).

11 

12## Install the plugin

13 

14[Install the Codex Security plugin](codex://plugins/install/codex-security?marketplace=openai-curated)

15 

16After installation, start a new thread in the repository you want to

17assess.

18 

191. Open Codex

20 

21 Start Codex from your repository:

22 

23 ```

24 codex

25 ```

262. Open the plugin browser

27 

28 Enter:

29 

30 ```

31 /plugins

32 ```

333. Install Codex Security

34 

35 Search for **Codex Security**, open it, and select `Install plugin`.

364. Start a new thread

37 

38 Start a new thread in the repository you are authorized to review.

39 

40## Choose a security workflow

41 

42Choose the narrowest workflow that answers your question. A diff-focused scan

43is faster to review than a repository-wide scan; a deep scan intentionally uses

44more time and tokens to search for more candidate findings.

45 

46| Goal | Skill | Scope and output |

47| --- | --- | --- |

48| Review a repository or one scoped path | `$codex-security:security-scan` | Runs threat modeling, finding discovery, validation, attack-path analysis, and produces Markdown and HTML reports. |

49| Run a higher-recall audit | `$codex-security:deep-security-scan` | Repeats repository-wide discovery with delegated workers before validation and reporting. Use it only for an entire repository. |

50| Review a change before merge | `$codex-security:security-diff-scan` | Reviews a pull request, commit, branch diff, or working-tree patch and produces a Markdown report grounded in changed code. |

51| Fix one finding | `$codex-security:fix-finding` | Reproduces or validates one plausible finding, makes a minimal fix when needed, and checks that the vulnerable behavior no longer reproduces. |

52 

53For example, to scan a repository:

54 

55```

56Use $codex-security:security-scan to scan this repository for security

57vulnerabilities. Keep the scan grounded in code evidence, validate plausible

58findings where feasible, and return the final report paths. Do not modify code.

59```

60 

61To review the current change instead:

62 

63```

64Use $codex-security:security-diff-scan to review the current branch diff for

65security regressions. Keep the review scoped to changed code and directly

66supporting files. Do not modify code.

67```

68 

69## Review the result and fix findings

70 

71Repository scans use a staged workflow:

72 

731. **Threat modeling** identifies entry points, trust boundaries, sensitive

74 actions, and risky components.

752. **Finding discovery** looks for concrete source-to-sink paths or broken

76 controls in the requested scope.

773. **Validation** tests or otherwise verifies plausible findings and records

78 evidence or proof gaps.

794. **Attack-path analysis** traces exploitable paths and rates severity for

80 findings that survive validation.

815. **Reporting** writes findings, affected locations, validation evidence,

82 remediation guidance, and review directives to artifacts.

83 

84An ordinary repository scan or a deep scan writes `report.md` and a readable

85`report.html` within its scan directory. A diff scan writes a focused Markdown

86report. Review affected files, evidence, assumptions, and severity before

87starting remediation.

88 

89When a finding is actionable, ask for a bounded fix:

90 

91```

92Use $codex-security:fix-finding to fix finding [finding ID or report

93reference]. Add focused regression coverage, verify legitimate behavior still

94works, and show that the original issue no longer reproduces. Do not broaden

95the change beyond this finding.

96```

97 

98## Keep security work authorized and reviewable

99 

100Run scans only against repositories, diffs, and systems that you own or that

101your organization authorizes you to assess. A finding is an input to review,

102not an instruction to merge code or test unrelated targets.

103 

104- Keep the first scan read-only unless you explicitly ask Codex to prepare a

105 fix.

106- Review commands that build, run, or reproduce behavior before approving

107 them, especially in unfamiliar repositories.

108- Review every proposed patch and validation result before merging it.

109- Keep repository instructions and approval policies in place while using the

110 plugin. For details, see [Agent approvals and security](https://developers.openai.com/codex/agent-approvals-security).

111 

112## Explore security use cases

113 

114- [Run a deep security scan](https://developers.openai.com/codex/use-cases/deep-security-scan)

115- [Scan code changes for security](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security)

116- [Remediate a vulnerability backlog](https://developers.openai.com/codex/use-cases/remediate-vulnerability-backlog)

117 

32 32 

33## Collections33## Collections

34 34 

35[Productivity & Collaboration Coordinate work across apps, data, and teams.](https://developers.openai.com/codex/use-cases/collections/productivity-and-collaboration) [Web development Build responsive UI from designs and prompts.](https://developers.openai.com/codex/use-cases/collections/web-development) [Game development Prototype loops, UI, and gameplay faster.](https://developers.openai.com/codex/use-cases/collections/game-development) [Native development Build and debug iOS and macOS apps.](https://developers.openai.com/codex/use-cases/collections/native-development) [Production systems Navigate, refactor, and review real codebases.](https://developers.openai.com/codex/use-cases/collections/production-systems)35[Productivity & Collaboration Coordinate work across apps, data, and teams.](https://developers.openai.com/codex/use-cases/collections/productivity-and-collaboration) [Web development Build responsive UI from designs and prompts.](https://developers.openai.com/codex/use-cases/collections/web-development) [Game development Prototype loops, UI, and gameplay faster.](https://developers.openai.com/codex/use-cases/collections/game-development) [Native development Build and debug iOS and macOS apps.](https://developers.openai.com/codex/use-cases/collections/native-development) [Production systems Navigate, refactor, and review real codebases.](https://developers.openai.com/codex/use-cases/collections/production-systems) [Security Find, review, and remediate vulnerabilities in authorized code.](https://developers.openai.com/codex/use-cases/collections/security)

36 36 

37## All use cases37## All use cases

38 38 

310 310 

311iOS Code](https://developers.openai.com/codex/use-cases/ios-simulator-bug-debugging)311iOS Code](https://developers.openai.com/codex/use-cases/ios-simulator-bug-debugging)

312 312 

313[![](https://developers.openai.com/codex/use-cases/dependency-incident-audits.webp)313[![](https://developers.openai.com/codex/use-cases/remediate-vulnerability-backlog.webp)

314 314 

315### Audit dependency incidents315### Remediate a vulnerability backlog

316 316 

317Turn a public package advisory into a safe repo-audit plan.317Turn reviewed findings into minimal fixes with regression evidence.

318 318 

319Engineering Quality](https://developers.openai.com/codex/use-cases/dependency-incident-audits)319Engineering Quality](https://developers.openai.com/codex/use-cases/remediate-vulnerability-backlog)

320 320 

321[![](https://developers.openai.com/codex/use-cases/meeting-prep-briefs.webp)321[![](https://developers.openai.com/codex/use-cases/deep-security-scan.webp)

322 322 

323### Prepare meeting briefs323### Run a deep security scan

324 324 

325Turn calendar context into an agenda and notes plan.325Search an authorized repository deeply for plausible vulnerabilities.

326 326 

327Integrations Knowledge Work](https://developers.openai.com/codex/use-cases/meeting-prep-briefs)327Engineering Quality](https://developers.openai.com/codex/use-cases/deep-security-scan)

328 328 

329[![](https://developers.openai.com/codex/use-cases/event-launch-playbooks.webp)329[![](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security.webp)

330 330 

331### Run event playbooks331### Scan code changes for security

332 332 

333Create repeatable workflows for event program management.333Review a pull request or local diff for security regressions.

334 334 

335Integrations Knowledge Work](https://developers.openai.com/codex/use-cases/event-launch-playbooks)335Engineering Quality](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security)

336 336 

337[![](https://developers.openai.com/codex/use-cases/code-migrations.webp)337[![](https://developers.openai.com/codex/use-cases/code-migrations.webp)

338 338 

454 454 

455Automation Integrations](https://developers.openai.com/codex/use-cases/zoom-meeting-follow-ups)455Automation Integrations](https://developers.openai.com/codex/use-cases/zoom-meeting-follow-ups)

456 456 

457[![](https://developers.openai.com/codex/use-cases/dependency-incident-audits.webp)

458 

459### Audit dependency incidents

460 

461Turn a public package advisory into a safe repo-audit plan.

462 

463Engineering Quality](https://developers.openai.com/codex/use-cases/dependency-incident-audits)

464 

465[![](https://developers.openai.com/codex/use-cases/meeting-prep-briefs.webp)

466 

467### Prepare meeting briefs

468 

469Turn calendar context into an agenda and notes plan.

470 

471Integrations Knowledge Work](https://developers.openai.com/codex/use-cases/meeting-prep-briefs)

472 

473[![](https://developers.openai.com/codex/use-cases/event-launch-playbooks.webp)

474 

475### Run event playbooks

476 

477Create repeatable workflows for event program management.

478 

479Integrations Knowledge Work](https://developers.openai.com/codex/use-cases/event-launch-playbooks)

480 

457## No use cases match these filters481## No use cases match these filters

458 482 

459Try clearing a few filters or searching for a broader term.483Try clearing a few filters or searching for a broader term.

162 162 

163Use `/goal` when a task needs Codex to keep working across turns toward a verifiable...163Use `/goal` when a task needs Codex to keep working across turns toward a verifiable...

164 164 

165Engineering Automation](https://developers.openai.com/codex/use-cases/follow-goals)[![](https://developers.openai.com/codex/use-cases/dependency-incident-audits.webp)165Engineering Automation](https://developers.openai.com/codex/use-cases/follow-goals)[![](https://developers.openai.com/codex/use-cases/remediate-vulnerability-backlog.webp)

166 166 

167### Audit dependency incidents167### Remediate a vulnerability backlog

168 168 

169Use Codex to turn a public package or supply chain advisory into a read-only audit, then...169Bring in approved findings from ticketing tools or vulnerability reporting systems, then use...

170 170 

171Engineering Quality](https://developers.openai.com/codex/use-cases/dependency-incident-audits)171Engineering Quality](https://developers.openai.com/codex/use-cases/remediate-vulnerability-backlog)

172 172 

149 149 

150## Related use cases150## Related use cases

151 151 

152[![](https://developers.openai.com/codex/use-cases/api-integration-migrations.webp)152[![](https://developers.openai.com/codex/use-cases/remediate-vulnerability-backlog.webp)

153 153 

154### Upgrade your API integration154### Remediate a vulnerability backlog

155 155 

156Use Codex to update your existing OpenAI API integration to the latest recommended models...156Bring in approved findings from ticketing tools or vulnerability reporting systems, then use...

157 157 

158Evaluation Engineering](https://developers.openai.com/codex/use-cases/api-integration-migrations)[![](https://developers.openai.com/codex/use-cases/dependency-incident-audits.webp)158Engineering Quality](https://developers.openai.com/codex/use-cases/remediate-vulnerability-backlog)[![](https://developers.openai.com/codex/use-cases/deep-security-scan.webp)

159 159 

160### Audit dependency incidents160### Run a deep security scan

161 161 

162Use Codex to turn a public package or supply chain advisory into a read-only audit, then...162Use the Codex Security plugin to run a higher-recall, repository-wide audit that repeats...

163 163 

164Engineering Quality](https://developers.openai.com/codex/use-cases/dependency-incident-audits)[![](https://developers.openai.com/codex/use-cases/agent-friendly-clis.webp)164Engineering Quality](https://developers.openai.com/codex/use-cases/deep-security-scan)[![](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security.webp)

165 165 

166### Create a CLI Codex can use166### Scan code changes for security

167 167 

168Ask Codex to create a composable CLI it can run from any folder, combine with repo scripts...168Use the Codex Security plugin to examine a Git-backed change set, validate plausible...

169 169 

170Engineering Code](https://developers.openai.com/codex/use-cases/agent-friendly-clis)170Engineering Quality](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security)

171 171 

109 109 

110Ask Codex to inspect your AI application, identify the behavior you want to evaluate, and...110Ask Codex to inspect your AI application, identify the behavior you want to evaluate, and...

111 111 

112Evaluation Quality](https://developers.openai.com/codex/use-cases/ai-app-evals)[![](https://developers.openai.com/codex/use-cases/macos-telemetry-logs.webp)112Evaluation Quality](https://developers.openai.com/codex/use-cases/ai-app-evals)[![](https://developers.openai.com/codex/use-cases/remediate-vulnerability-backlog.webp)

113 113 

114### Add Mac telemetry114### Remediate a vulnerability backlog

115 115 

116Use Codex and the Build macOS Apps plugin to add a few high-signal `Logger` events around...116Bring in approved findings from ticketing tools or vulnerability reporting systems, then use...

117 117 

118macOS Code](https://developers.openai.com/codex/use-cases/macos-telemetry-logs)[![](https://developers.openai.com/codex/use-cases/react-native-expo-apps.webp)118Engineering Quality](https://developers.openai.com/codex/use-cases/remediate-vulnerability-backlog)[![](https://developers.openai.com/codex/use-cases/macos-telemetry-logs.webp)

119 119 

120### Build React Native apps with Expo120### Add Mac telemetry

121 121 

122Use Codex with the Expo plugin to scaffold React Native apps, stay inside Expo Router and...122Use Codex and the Build macOS Apps plugin to add a few high-signal `Logger` events around...

123 123 

124Mobile Engineering](https://developers.openai.com/codex/use-cases/react-native-expo-apps)124macOS Code](https://developers.openai.com/codex/use-cases/macos-telemetry-logs)

125 125 

1# Use case collections1# Use case collections

2 2 

3[Productivity & Collaboration Coordinate work across apps, data, and teams.](https://developers.openai.com/codex/use-cases/collections/productivity-and-collaboration) [Web development Build responsive UI from designs and prompts.](https://developers.openai.com/codex/use-cases/collections/web-development) [Game development Prototype loops, UI, and gameplay faster.](https://developers.openai.com/codex/use-cases/collections/game-development) [Native development Build and debug iOS and macOS apps.](https://developers.openai.com/codex/use-cases/collections/native-development) [Production systems Navigate, refactor, and review real codebases.](https://developers.openai.com/codex/use-cases/collections/production-systems)3[Productivity & Collaboration Coordinate work across apps, data, and teams.](https://developers.openai.com/codex/use-cases/collections/productivity-and-collaboration) [Web development Build responsive UI from designs and prompts.](https://developers.openai.com/codex/use-cases/collections/web-development) [Game development Prototype loops, UI, and gameplay faster.](https://developers.openai.com/codex/use-cases/collections/game-development) [Native development Build and debug iOS and macOS apps.](https://developers.openai.com/codex/use-cases/collections/native-development) [Production systems Navigate, refactor, and review real codebases.](https://developers.openai.com/codex/use-cases/collections/production-systems) [Security Find, review, and remediate vulnerabilities in authorized code.](https://developers.openai.com/codex/use-cases/collections/security)

4 4 

1# Security – Codex

2 

3Use the Codex Security plugin to assess code you have permission to review and

4turn evidence into bounded remediation work. Start with read-only detection,

5review findings, and approve changes deliberately.

6 

7## Find, validate, and fix vulnerabilities

8 

9Scan an authorized repository or code change, validate reviewed findings, and

10prepare focused fixes with evidence for approval.

11 

12[![](https://developers.openai.com/codex/use-cases/deep-security-scan.webp)

13 

14### Run a deep security scan

15 

16Use the Codex Security plugin to run a higher-recall, repository-wide audit that repeats...

17 

18Engineering Quality](https://developers.openai.com/codex/use-cases/deep-security-scan)[![](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security.webp)

19 

20### Scan code changes for security

21 

22Use the Codex Security plugin to examine a Git-backed change set, validate plausible...

23 

24Engineering Quality](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security)[![](https://developers.openai.com/codex/use-cases/remediate-vulnerability-backlog.webp)

25 

26### Remediate a vulnerability backlog

27 

28Bring in approved findings from ticketing tools or vulnerability reporting systems, then use...

29 

30Engineering Quality](https://developers.openai.com/codex/use-cases/remediate-vulnerability-backlog)

31 

1# Run a deep security scan | Codex use cases

2 

3Codex use cases

4 

5![](/assets/OpenAI-black-wordmark.svg)

6 

7![Codex](/assets/OAI_Codex-Lockup_Fallback_Black.svg)

8 

9Codex use case

10 

11# Run a deep security scan

12 

13Search an authorized repository deeply for plausible vulnerabilities.

14 

15Difficulty **Advanced**

16 

17Time horizon **Long-running**

18 

19Use the Codex Security plugin to run a higher-recall, repository-wide audit that repeats discovery, validates candidates, and produces reviewable report artifacts.

20 

21## Best for

22 

23- Application security reviews of a complete repository that you own or are authorized to assess.

24- High-recall reviews where additional runtime and token use are appropriate for finding more candidate issues.

25- Security teams that need traceable finding evidence before deciding what to remediate.

26 

27# Contents

28 

29[← All use cases](https://developers.openai.com/codex/use-cases)

30 

31Copy page [Export as PDF](https://developers.openai.com/codex/use-cases/deep-security-scan/?export=pdf)

32 

33Use the Codex Security plugin to run a higher-recall, repository-wide audit that repeats discovery, validates candidates, and produces reviewable report artifacts.

34 

35Advanced

36 

37Long-running

38 

39Related links

40 

41[Codex Security plugin](https://developers.openai.com/codex/security/plugin) [Agent approvals and security](https://developers.openai.com/codex/agent-approvals-security) [Codex cyber safety](https://developers.openai.com/codex/concepts/cyber-safety)

42 

43## Best for

44 

45- Application security reviews of a complete repository that you own or are authorized to assess.

46- High-recall reviews where additional runtime and token use are appropriate for finding more candidate issues.

47- Security teams that need traceable finding evidence before deciding what to remediate.

48 

49## Skills & Plugins

50 

51- [Codex Security:deep Security Scan](https://developers.openai.com/codex/security/plugin)

52 

53 Run repeated repository-wide security discovery passes, validate surviving findings, analyze attack paths, and create reviewable reports.

54 

55| Skill | Why use it |

56| --- | --- |

57| [Codex Security:deep Security Scan](https://developers.openai.com/codex/security/plugin) | Run repeated repository-wide security discovery passes, validate surviving findings, analyze attack paths, and create reviewable reports. |

58 

59## Starter prompt

60 

61/goal Run a deep security scan on this repository. Do not stop until all required steps are complete and the final report is ready.

62Scope and rules:

63- I am authorized to assess this repository.

64- Treat the entire repository as in scope.

65- Use the Codex Security plugin's deep scan workflow; do not broaden this into a diff or scoped-path review.

66- Keep the scan read-only; do not modify code, open pull requests, or test external targets.

67Return the final Markdown and HTML report paths and summarize the findings that require human review first.

68 

69[Open in the Codex app](codex://threads/new?prompt=%2Fgoal+Run+a+deep+security+scan+on+this+repository.+Do+not+stop+until+all+required+steps+are+complete+and+the+final+report+is+ready.%0A%0AScope+and+rules%3A%0A-+I+am+authorized+to+assess+this+repository.%0A-+Treat+the+entire+repository+as+in+scope.%0A-+Use+the+Codex+Security+plugin%27s+deep+scan+workflow%3B+do+not+broaden+this+into+a+diff+or+scoped-path+review.%0A-+Keep+the+scan+read-only%3B+do+not+modify+code%2C+open+pull+requests%2C+or+test+external+targets.%0A%0AReturn+the+final+Markdown+and+HTML+report+paths+and+summarize+the+findings+that+require+human+review+first. "Open in the Codex app")

70 

71/goal Run a deep security scan on this repository. Do not stop until all required steps are complete and the final report is ready.

72Scope and rules:

73- I am authorized to assess this repository.

74- Treat the entire repository as in scope.

75- Use the Codex Security plugin's deep scan workflow; do not broaden this into a diff or scoped-path review.

76- Keep the scan read-only; do not modify code, open pull requests, or test external targets.

77Return the final Markdown and HTML report paths and summarize the findings that require human review first.

78 

79## Choose a deep repository review

80 

81Use a deep scan when you need high-recall vulnerability discovery across a

82complete repository and can budget for a longer run. The Codex Security plugin

83repeats discovery passes before validating and prioritizing findings, so this

84workflow takes more time and tokens than an ordinary scan.

85 

86A deep scan is for an entire repository. To review one package or directory,

87use `$codex-security:security-scan`. To review a pull request, commit, branch

88diff, or working-tree patch, use

89[$codex-security:security-diff-scan](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security).

90 

91## Prepare an authorized scan

92 

931. Open the repository in Codex and install the [Codex Security plugin](https://developers.openai.com/codex/security/plugin).

942. Confirm that you own the repository or have authorization to assess it.

953. Add repository-specific architecture, trust-boundary, build, test, and validation guidance in `AGENTS.md` when it will improve the review.

964. Run the starter prompt and let the scan complete its repeated discovery, validation, attack-path analysis, and final reporting stages.

975. Review the final reports before asking Codex to change code or reproduce a finding further.

98 

99## Review evidence before remediation

100 

101The final result should identify affected locations, why the behavior is

102reachable, what validation Codex performed, any remaining proof gaps, and a

103bounded remediation direction. Distinguish findings without validation evidence

104from validated findings.

105 

106Start remediation only for a finding you have selected and reviewed. Use

107[Remediate a vulnerability backlog](https://developers.openai.com/codex/use-cases/remediate-vulnerability-backlog)

108to fix findings one at a time with focused regression validation.

109 

110## Related use cases

111 

112[![](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security.webp)

113 

114### Scan code changes for security

115 

116Use the Codex Security plugin to examine a Git-backed change set, validate plausible...

117 

118Engineering Quality](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security)[![](https://developers.openai.com/codex/use-cases/ai-app-evals.webp)

119 

120### Add evals to your AI application

121 

122Ask Codex to inspect your AI application, identify the behavior you want to evaluate, and...

123 

124Evaluation Quality](https://developers.openai.com/codex/use-cases/ai-app-evals)[![](https://developers.openai.com/codex/use-cases/dependency-incident-audits.webp)

125 

126### Audit dependency incidents

127 

128Use Codex to turn a public package or supply chain advisory into a read-only audit, then...

129 

130Engineering Quality](https://developers.openai.com/codex/use-cases/dependency-incident-audits)

131 

148 148 

149## Related use cases149## Related use cases

150 150 

151[![](https://developers.openai.com/codex/use-cases/ai-app-evals.webp)151[![](https://developers.openai.com/codex/use-cases/deep-security-scan.webp)

152 152 

153### Add evals to your AI application153### Run a deep security scan

154 154 

155Ask Codex to inspect your AI application, identify the behavior you want to evaluate, and...155Use the Codex Security plugin to run a higher-recall, repository-wide audit that repeats...

156 156 

157Evaluation Quality](https://developers.openai.com/codex/use-cases/ai-app-evals)[![](https://developers.openai.com/codex/use-cases/agent-friendly-clis.webp)157Engineering Quality](https://developers.openai.com/codex/use-cases/deep-security-scan)[![](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security.webp)

158 158 

159### Create a CLI Codex can use159### Scan code changes for security

160 160 

161Ask Codex to create a composable CLI it can run from any folder, combine with repo scripts...161Use the Codex Security plugin to examine a Git-backed change set, validate plausible...

162 162 

163Engineering Code](https://developers.openai.com/codex/use-cases/agent-friendly-clis)[![](https://developers.openai.com/codex/use-cases/follow-goals.webp)163Engineering Quality](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security)[![](https://developers.openai.com/codex/use-cases/ai-app-evals.webp)

164 164 

165### Follow a goal165### Add evals to your AI application

166 166 

167Use `/goal` when a task needs Codex to keep working across turns toward a verifiable...167Ask Codex to inspect your AI application, identify the behavior you want to evaluate, and...

168 168 

169Engineering Automation](https://developers.openai.com/codex/use-cases/follow-goals)169Evaluation Quality](https://developers.openai.com/codex/use-cases/ai-app-evals)

170 170 

1# Remediate a vulnerability backlog | Codex use cases

2 

3Codex use cases

4 

5![](/assets/OpenAI-black-wordmark.svg)

6 

7![Codex](/assets/OAI_Codex-Lockup_Fallback_Black.svg)

8 

9Codex use case

10 

11# Remediate a vulnerability backlog

12 

13Turn reviewed findings into minimal fixes with regression evidence.

14 

15Difficulty **Advanced**

16 

17Time horizon **1h**

18 

19Bring in approved findings from ticketing tools or vulnerability reporting systems, then use the Codex Security plugin to validate and address them one at a time with bounded patches and regression evidence.

20 

21## Best for

22 

23- Teams with reviewed findings from Codex Security, Linear or Jira tickets, GitHub Security Advisories, HackerOne or Bugcrowd reports, penetration tests, or internal security reviews.

24- Vulnerability backlogs where every patch needs a minimal diff and repeatable validation.

25- Maintainers who want to separate security remediation from broader refactors or cleanup.

26 

27# Contents

28 

29[← All use cases](https://developers.openai.com/codex/use-cases)

30 

31Copy page [Export as PDF](https://developers.openai.com/codex/use-cases/remediate-vulnerability-backlog/?export=pdf)

32 

33Bring in approved findings from ticketing tools or vulnerability reporting systems, then use the Codex Security plugin to validate and address them one at a time with bounded patches and regression evidence.

34 

35Advanced

36 

371h

38 

39Related links

40 

41[Codex Security plugin](https://developers.openai.com/codex/security/plugin) [Run a deep security scan](https://developers.openai.com/codex/use-cases/deep-security-scan) [Scan code changes for security](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security)

42 

43## Best for

44 

45- Teams with reviewed findings from Codex Security, Linear or Jira tickets, GitHub Security Advisories, HackerOne or Bugcrowd reports, penetration tests, or internal security reviews.

46- Vulnerability backlogs where every patch needs a minimal diff and repeatable validation.

47- Maintainers who want to separate security remediation from broader refactors or cleanup.

48 

49## Skills & Plugins

50 

51- [Codex Security:fix Finding](https://developers.openai.com/codex/security/plugin)

52 

53 Fix and verify one validated or plausible security finding with focused tests or reproduction evidence.

54 

55| Skill | Why use it |

56| --- | --- |

57| [Codex Security:fix Finding](https://developers.openai.com/codex/security/plugin) | Fix and verify one validated or plausible security finding with focused tests or reproduction evidence. |

58 

59## Starter prompt

60 

61Use $codex-security:fix-finding to fix this security finding and verify the issue no longer reproduces.

62Source: [Codex Security report / Linear or Jira ticket / GitHub Security Advisory / HackerOne or Bugcrowd report / other authorized source]

63Title and affected component: [finding title and component]

64Vulnerable source, sink, or broken control: [known path or unknown]

65Attacker-controlled input and impact: [input, prerequisites, and impact]

66Expected security invariant: [behavior the fix must enforce]

67Existing proof: [report path, PoC, reproducer, test, or validation notes]

68Affected files and lines: [paths and lines, or unknown]

69Constraints: [supported behavior to preserve, test command, rollout requirement, or none]

70Requirements:

71- Confirm that the issue still exists before changing code when feasible.

72- Make the smallest change that enforces the intended security invariant.

73- Add focused regression coverage or the strongest repeatable validation artifact available.

74- Verify legitimate behavior still works and the original issue no longer reproduces.

75- Keep unrelated backlog findings and refactors out of this change.

76Report the changed files, tests or validation artifacts, exact commands and results, proof that the original issue no longer reproduces, and remaining uncertainty. If the issue is already fixed, show the evidence and do not change code.

77 

78[Open in the Codex app](codex://threads/new?prompt=Use+%24codex-security%3Afix-finding+to+fix+this+security+finding+and+verify+the+issue+no+longer+reproduces.%0A%0ASource%3A+%5BCodex+Security+report+%2F+Linear+or+Jira+ticket+%2F+GitHub+Security+Advisory+%2F+HackerOne+or+Bugcrowd+report+%2F+other+authorized+source%5D%0ATitle+and+affected+component%3A+%5Bfinding+title+and+component%5D%0AVulnerable+source%2C+sink%2C+or+broken+control%3A+%5Bknown+path+or+unknown%5D%0AAttacker-controlled+input+and+impact%3A+%5Binput%2C+prerequisites%2C+and+impact%5D%0AExpected+security+invariant%3A+%5Bbehavior+the+fix+must+enforce%5D%0AExisting+proof%3A+%5Breport+path%2C+PoC%2C+reproducer%2C+test%2C+or+validation+notes%5D%0AAffected+files+and+lines%3A+%5Bpaths+and+lines%2C+or+unknown%5D%0AConstraints%3A+%5Bsupported+behavior+to+preserve%2C+test+command%2C+rollout+requirement%2C+or+none%5D%0A%0ARequirements%3A%0A-+Confirm+that+the+issue+still+exists+before+changing+code+when+feasible.%0A-+Make+the+smallest+change+that+enforces+the+intended+security+invariant.%0A-+Add+focused+regression+coverage+or+the+strongest+repeatable+validation+artifact+available.%0A-+Verify+legitimate+behavior+still+works+and+the+original+issue+no+longer+reproduces.%0A-+Keep+unrelated+backlog+findings+and+refactors+out+of+this+change.%0A%0AReport+the+changed+files%2C+tests+or+validation+artifacts%2C+exact+commands+and+results%2C+proof+that+the+original+issue+no+longer+reproduces%2C+and+remaining+uncertainty.+If+the+issue+is+already+fixed%2C+show+the+evidence+and+do+not+change+code. "Open in the Codex app")

79 

80Use $codex-security:fix-finding to fix this security finding and verify the issue no longer reproduces.

81Source: [Codex Security report / Linear or Jira ticket / GitHub Security Advisory / HackerOne or Bugcrowd report / other authorized source]

82Title and affected component: [finding title and component]

83Vulnerable source, sink, or broken control: [known path or unknown]

84Attacker-controlled input and impact: [input, prerequisites, and impact]

85Expected security invariant: [behavior the fix must enforce]

86Existing proof: [report path, PoC, reproducer, test, or validation notes]

87Affected files and lines: [paths and lines, or unknown]

88Constraints: [supported behavior to preserve, test command, rollout requirement, or none]

89Requirements:

90- Confirm that the issue still exists before changing code when feasible.

91- Make the smallest change that enforces the intended security invariant.

92- Add focused regression coverage or the strongest repeatable validation artifact available.

93- Verify legitimate behavior still works and the original issue no longer reproduces.

94- Keep unrelated backlog findings and refactors out of this change.

95Report the changed files, tests or validation artifacts, exact commands and results, proof that the original issue no longer reproduces, and remaining uncertainty. If the issue is already fixed, show the evidence and do not change code.

96 

97## Fix reviewed findings one at a time

98 

99Use this workflow after a security finding has enough evidence for a bounded

100remediation decision. The finding can come from the Codex Security plugin, an

101issue tracker such as Linear or Jira, GitHub Security Advisories, a disclosure

102platform such as HackerOne or Bugcrowd, an internal review, or another

103authorized source. Connect the source where supported, or provide the report,

104ticket, or advisory with affected code and evidence whenever possible.

105 

106Don’t hand Codex a broad backlog and ask it to change everything at once. A

107single-finding loop keeps the security invariant, patch, and validation

108evidence reviewable.

109 

110## Close one item with evidence

111 

1121. Select a finding from Codex Security, a ticketing system, a security advisory, a disclosure platform, or another source your team authorizes for remediation.

1132. Provide or retrieve its source reference, source or broken control, attacker-controlled input, affected files, reproduction evidence, and intended secure behavior.

1143. Ask `$codex-security:fix-finding` to reproduce or validate the issue before making a minimal patch, or to report that no code change is needed if it is already fixed.

1154. Review the regression test or validation artifact alongside the patch.

1165. Confirm that legitimate behavior remains supported and that the original vulnerable path no longer reproduces.

1176. Record remaining uncertainty before selecting the next item.

118 

119## Keep the backlog auditable

120 

121For each completed item, keep the original ticket, advisory, or report

122reference; the exact code change; the checks run; and any proof gap. If Codex

123finds that the issue is already fixed or it can’t reproduce it, record that

124evidence instead of forcing an unnecessary code change.

125 

126## Related use cases

127 

128[![](https://developers.openai.com/codex/use-cases/ai-app-evals.webp)

129 

130### Add evals to your AI application

131 

132Ask Codex to inspect your AI application, identify the behavior you want to evaluate, and...

133 

134Evaluation Quality](https://developers.openai.com/codex/use-cases/ai-app-evals)[![](https://developers.openai.com/codex/use-cases/deep-security-scan.webp)

135 

136### Run a deep security scan

137 

138Use the Codex Security plugin to run a higher-recall, repository-wide audit that repeats...

139 

140Engineering Quality](https://developers.openai.com/codex/use-cases/deep-security-scan)[![](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security.webp)

141 

142### Scan code changes for security

143 

144Use the Codex Security plugin to examine a Git-backed change set, validate plausible...

145 

146Engineering Quality](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security)

147 

1# Scan code changes for security | Codex use cases

2 

3Codex use cases

4 

5![](/assets/OpenAI-black-wordmark.svg)

6 

7![Codex](/assets/OAI_Codex-Lockup_Fallback_Black.svg)

8 

9Codex use case

10 

11# Scan code changes for security

12 

13Review a pull request or local diff for security regressions.

14 

15Difficulty **Intermediate**

16 

17Time horizon **30m**

18 

19Use the Codex Security plugin to examine a Git-backed change set, validate plausible security regressions, and produce an evidence-based report before merge.

20 

21## Best for

22 

23- Pull requests that touch authentication, authorization, parsing, file access, secrets, or privileged workflows.

24- Release branches or local patches that need a security-focused check before merge.

25- Reviewers who need findings anchored to changed code and directly supporting files.

26 

27# Contents

28 

29[← All use cases](https://developers.openai.com/codex/use-cases)

30 

31Copy page [Export as PDF](https://developers.openai.com/codex/use-cases/scan-code-changes-for-security/?export=pdf)

32 

33Use the Codex Security plugin to examine a Git-backed change set, validate plausible security regressions, and produce an evidence-based report before merge.

34 

35Intermediate

36 

3730m

38 

39Related links

40 

41[Codex Security plugin](https://developers.openai.com/codex/security/plugin) [Review GitHub pull requests](https://developers.openai.com/codex/use-cases/github-code-reviews) [Agent approvals and security](https://developers.openai.com/codex/agent-approvals-security)

42 

43## Best for

44 

45- Pull requests that touch authentication, authorization, parsing, file access, secrets, or privileged workflows.

46- Release branches or local patches that need a security-focused check before merge.

47- Reviewers who need findings anchored to changed code and directly supporting files.

48 

49## Skills & Plugins

50 

51- [Codex Security:security Diff Scan](https://developers.openai.com/codex/security/plugin)

52 

53 Review a pull request, commit, branch diff, or working-tree patch for security regressions with validation and attack-path evidence.

54 

55| Skill | Why use it |

56| --- | --- |

57| [Codex Security:security Diff Scan](https://developers.openai.com/codex/security/plugin) | Review a pull request, commit, branch diff, or working-tree patch for security regressions with validation and attack-path evidence. |

58 

59## Starter prompt

60 

61/goal Scan this PR, commit, branch diff, or working-tree patch for security regressions. Do not stop until all in-scope changed files are covered and all required steps are complete.

62Scope and rules:

63- Target: [this pull request / commit SHA / branch diff from BASE to HEAD / the current working-tree patch]

64- I am authorized to assess this repository and change set.

65- Pay particular attention to [auth, input handling, secrets, filesystem, network, dependencies, or other sensitive surface].

66- Keep this pass read-only; do not modify code or open a pull request.

67Return the final Markdown report and any Codex app review directives for findings that require human review.

68 

69[Open in the Codex app](codex://threads/new?prompt=%2Fgoal+Scan+this+PR%2C+commit%2C+branch+diff%2C+or+working-tree+patch+for+security+regressions.+Do+not+stop+until+all+in-scope+changed+files+are+covered+and+all+required+steps+are+complete.%0A%0AScope+and+rules%3A%0A-+Target%3A+%5Bthis+pull+request+%2F+commit+SHA+%2F+branch+diff+from+BASE+to+HEAD+%2F+the+current+working-tree+patch%5D%0A-+I+am+authorized+to+assess+this+repository+and+change+set.%0A-+Pay+particular+attention+to+%5Bauth%2C+input+handling%2C+secrets%2C+filesystem%2C+network%2C+dependencies%2C+or+other+sensitive+surface%5D.%0A-+Keep+this+pass+read-only%3B+do+not+modify+code+or+open+a+pull+request.%0A%0AReturn+the+final+Markdown+report+and+any+Codex+app+review+directives+for+findings+that+require+human+review. "Open in the Codex app")

70 

71/goal Scan this PR, commit, branch diff, or working-tree patch for security regressions. Do not stop until all in-scope changed files are covered and all required steps are complete.

72Scope and rules:

73- Target: [this pull request / commit SHA / branch diff from BASE to HEAD / the current working-tree patch]

74- I am authorized to assess this repository and change set.

75- Pay particular attention to [auth, input handling, secrets, filesystem, network, dependencies, or other sensitive surface].

76- Keep this pass read-only; do not modify code or open a pull request.

77Return the final Markdown report and any Codex app review directives for findings that require human review.

78 

79## Review the change instead of the whole repository

80 

81Use a security diff scan when a pull request, commit, branch, or local patch

82changes a sensitive code path. The Codex Security plugin uses repository

83context to understand the change, then keeps finding discovery and validation

84focused on the diff and directly supporting code.

85 

86This workflow complements ordinary code review. Use it when you want evidence

87about security regressions, not a general style or test review.

88 

89## Run a focused pass

90 

911. Open the repository and check out or describe the exact Git-backed change set to review.

922. Install the [Codex Security plugin](https://developers.openai.com/codex/security/plugin) and specify the pull request, commit, branch diff, or working-tree patch in the starter prompt.

933. Name high-risk surfaces in the change, such as authentication, parsers, file paths, network requests, or credential handling.

944. Run the prompt without requesting a fix so the first result remains a review artifact.

955. Check each reported affected line, validation result, and stated proof gap before deciding whether to remediate.

96 

97## Follow through on a finding

98 

99A useful report distinguishes a reachable, supported security finding from a

100suspicion that still needs confirmation and can include Codex app review

101directives for affected lines. For an actionable result, open a new bounded

102fix task with the finding identifier or the relevant report section.

103See [Remediate a vulnerability backlog](https://developers.openai.com/codex/use-cases/remediate-vulnerability-backlog)

104for the fix-and-validation loop.

105 

106## Related use cases

107 

108[![](https://developers.openai.com/codex/use-cases/deep-security-scan.webp)

109 

110### Run a deep security scan

111 

112Use the Codex Security plugin to run a higher-recall, repository-wide audit that repeats...

113 

114Engineering Quality](https://developers.openai.com/codex/use-cases/deep-security-scan)[![](https://developers.openai.com/codex/use-cases/ai-app-evals.webp)

115 

116### Add evals to your AI application

117 

118Ask Codex to inspect your AI application, identify the behavior you want to evaluate, and...

119 

120Evaluation Quality](https://developers.openai.com/codex/use-cases/ai-app-evals)[![](https://developers.openai.com/codex/use-cases/dependency-incident-audits.webp)

121 

122### Audit dependency incidents

123 

124Use Codex to turn a public package or supply chain advisory into a read-only audit, then...

125 

126Engineering Quality](https://developers.openai.com/codex/use-cases/dependency-incident-audits)

127