agentsclimarketplace

Forerunner audit

Skill derek-palmer/codeforerunner/skills/forerunner-audit

Run a security and dependency audit against a repository. Use when the user wants a security review, dependency vulnerability check, or supply-chain audit.From its SKILL.md

Install
npx -y skills add derek-palmer/codeforerunner --skill forerunner-audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.4 KB, as published. Nobody here has run it

forerunner-audit

Produces a structured security and dependency audit report. Covers known vulnerability patterns, dependency hygiene, secret exposure risks, and supply-chain concerns.

Activate when

User asks to: audit the repo, run a security check, check for vulnerabilities, review dependencies for security issues.

Collect this context

  • Scan result (run /forerunner-scan first)
  • All manifest and lockfiles: package.json, package-lock.json, yarn.lock, pyproject.toml, poetry.lock, requirements*.txt, go.mod, go.sum, Cargo.toml, Cargo.lock, Gemfile.lock
  • CI/CD workflow files
  • Dockerfile and compose files
  • .env.example or similar (never actual secret files)

Execute

Run forerunner generate --prompt-only audit — outputs the assembled prompt bundle to stdout. Read this output and execute the documentation task it describes.

Without CLI, get the prompt from:

  • src/codeforerunner/prompts/tasks/audit.md
  • src/codeforerunner/prompts/system/base.md

Output

Structured audit report covering: outdated/vulnerable dependencies, hardcoded secrets risk surface, CI security posture, supply-chain exposure. Severity-tagged findings (HIGH / MEDIUM / LOW). Write to docs/audit.md or return as Markdown.

Keep looking

Skills are one crate of 609,856. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.