agentleFS
Sign inStart free
loganware05loganware05/captains-compass-cursor/.cursor/skills/security-audit-procedures/SKILL.md

security-audit-procedures

Skill2 starsChanged 32 days agoMITView on GitHub

Runs structured security-audit checklists for agent workflows and Skill promotions alongside security-review

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check secrets handling, path traversal, and unsafe shell/git patterns in scripts and hooks.

    line 31
  2. Very specific:

    Verify promotions never set approved_for_execution: true on TI candidates and never auto-install into .cursor/skills/.

    line 33
  3. Distinctive:

    Do not clone or execute the starred audit toolkit

    line 46
  4. Distinctive:

    Do not weaken fail-closed hooks to pass an audit

    line 47
  5. Distinctive:

    Do not treat Linear/Overseer status as Captain approval

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Security Audit Procedures

Use this Skill when

Performing a structured security audit of agent workflows, Skill promotions, hooks, or TI/learning artifacts — complementary to Skill security-review.

Origin

  • Starred discovery: cloudflare/security-audit-skill
  • Candidate: github-stars-cloudflare-security-audit-skill
  • Lifecycle: AVAILABLE_SKILL (Captain-promoted Wave 1 / OVA-71)
  • Metadata/procedure only — do not clone or execute the starred repo

Inputs

  • Diff / changed files or Learning Loop candidate package
  • TI scorecards when promoting Stars-derived Skills
  • Hook / control-plane change set when applicable

Procedure

  1. Confirm trust boundary: discovery signal vs executable dependency.
  2. For Stars-derived Skills, require M23 scorecards (security-review + dependency-supply-chain) before AVAILABLE proposals.
  3. Check secrets handling, path traversal, and unsafe shell/git patterns in scripts and hooks.
  4. Verify promotions never set approved_for_execution: true on TI candidates and never auto-install into .cursor/skills/.
  5. For control-plane changes, cross-check Skill security-review fail-closed items (plan-approval, protected branch, soft-hook skips).
  6. Record findings under .agent/evidence/security/ with severity and remediation.

Output

  • Security audit notes / evidence markdown
  • Go/no-go for Skill promote or PR merge

Prohibited actions

  • Do not clone or execute the starred audit toolkit
  • Do not weaken fail-closed hooks to pass an audit
  • Do not treat Linear/Overseer status as Captain approval

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free