agentleFS
Sign inStart free
PantaniPantani/ableton-mind/.claude/skills/security-audit/SKILL.md

security-audit

Skill9 starsChanged 5 months agoMITView on GitHub

Security and supply-chain audit for ableton-mind. Use for dependency audit, install scripts, JSON-RPC bridge safety, workflow permissions, Docker, secrets, provenance, path handling, child processes and release security.

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 174 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill for practical security review of ableton-mind.

    line 8
  2. Very specific:

    Run dependency audit when available: npm audit --omit=dev.

    line 13
  3. Distinctive:

    Search for risky surfaces: child processes, eval-like execution, filesystem writes, network listeners, path joins, environment variables …

    line 14
  4. Very specific:

    Write _workspace/quality-audit/security-{N}.md with findings that include all required fields from the "Finding Requirements" section above.

    line 31
  5. Distinctive:

    Do not report generic "dependency exists" noise without an affected path.

    line 35

“Common” is measured: kept by at least 6 in 10 of the 174 edited versions of this file we could read. “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

Use this skill for practical security review of ableton-mind.

Workflow

  1. Inspect package scripts before executing them.
  2. Run dependency audit when available: npm audit --omit=dev.
  3. Search for risky surfaces: child processes, eval-like execution, filesystem writes, network listeners, path joins, environment variables and secret use.
  4. Review JSON-RPC bridge input validation, handler dispatch, error handling, localhost exposure and listener notifications.
  5. Review GitHub Actions permissions, token use, release provenance and Docker publishing.
  6. Rank issues by exploitability and affected user.

Finding Requirements

Each finding must include:

  • Severity.
  • File and line when possible.
  • Attack or misuse path.
  • Why this matters for a local MCP/Remote Script project.
  • Suggested fix.
  • Verification command or review step.

Report Format

Write _workspace/quality-audit/security-{N}.md with findings that include all required fields from the "Finding Requirements" section above.

Non-Goals

Do not report generic "dependency exists" noise without an affected path. Do not run external write or publish actions while auditing.

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