Index of every page on this site: llms.txt
All skills
openai avatar

/security-scan

@ec0d6c1
by openaiopenai/codex-security14k stars
1,108
Run it yourself

Find vulnerabilities in the current source of a whole repository or selected paths. This is the default single-pass audit. Use the diff skill for PR, commit, branch, or working-tree changes and the deep skill for an explicitly requested deep scan.

Use this Skill: https://skilld.dev/gh/openai/codex-security/security-scan

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesmanaged-scan.md

≈339 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Start or resume a managed Standard scan

Use the bound scan’s target, scope, user context, ID, directory and token for every update. If the handoff failed or identifies a different mode, stop before source review. Resume the saved phase. For an older handoff still in preflight, advance it to threat_model once.

If the host supplies a target-paths file without a prepared inventory, resolve it using scoped paths before review.

During review

Advance the current scan with update_codex_security_scan_progress at real forward transitions. Publish discovery before dispatch, validation before checking candidates, attack_path before reachability assessment, and reporting before final assembly. Keep the current phase when work overlaps. When bound, persist user-requested context changes through update_codex_security_scan_context with the complete replacement and token. Use the returned structuredContent.scan.userContext from each progress transition for that phase and its workers.

Increase the investigator total before dispatching new assignments, excluding the independent baseline. Record completed investigations as coverage surfaces before advancing their review_receipts count. Advance other counts only when the corresponding work exists. Publish meaningful batches without creating receipt files.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts8d3 checks · Risk SAFE
  • Gen Agent Trust Hub8d

    This skill facilitates automated security audits by utilizing local scripts to analyze repository source code. It includes built-in safeguards, such as explicit instructions to treat input files as data and to avoid following external links, which help maintain a secure analysis environment. The use of platform-specific commands is consistent with the skill's role as a cross-platform development tool.

  • Socket9d

    No alerts

  • Snyk8d

    Risk: LOW · No issues

Signed by skilld at ec0d6c1. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last week

README badge

README badge for openai/codex-security/security-scan