agentleFS
Sign inStart free
ArcQian-bitArcQian-bit/codex-real-engineer-skills/skills/security-scout/SKILL.md

security-scout

Skill1 starsChanged 5 months agoMITView on GitHub

Perform practical security review for code, diffs, dependencies, configuration, auth flows, data handling, and deployment changes. Use when the user asks for security audit, threat model, vulnerability review, secret scan, authz/authn check, injection risk, supply-chain risk, or secure implementation guidance. Do not use for exploit development or unrelated style review.

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check the risk categories that fit the change.

    line 15
  2. Distinctive:

    If a secret-like value appears, do not print the full value.

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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 Scout

Find realistic security risks and fix paths.

Workflow

  1. Identify assets: secrets, user data, money movement, permissions, tokens, files, network calls, admin surfaces, and logs.
  2. Identify trust boundaries: browser/server, user/admin, tenant/tenant, internal/external, CI/runtime.
  3. Review the changed code and the closest callers, validators, policies, and tests.
  4. Check the risk categories that fit the change.
  5. Recommend safe fixes and verification.

Risk Categories

  • Authentication bypass or weak session handling.
  • Authorization and tenant-boundary mistakes.
  • Injection: SQL, command, template, path, SSRF, XSS, deserialization.
  • Secret exposure in code, logs, errors, URLs, screenshots, or build artifacts.
  • Unsafe file upload/download or path traversal.
  • Dependency, package script, lockfile, and CI supply-chain risk.
  • Missing rate limits, replay protection, CSRF, or input limits.
  • Insecure defaults in deployment, CORS, cookies, TLS, or cloud IAM.

Reporting

For each finding include:

  • Severity: Critical, High, Medium, or Low.
  • Preconditions: what an attacker needs.
  • Impact: what they gain or break.
  • Evidence: exact code path.
  • Fix: concrete mitigation.
  • Verification: test, scan, or manual check.

If a secret-like value appears, do not print the full value. Show only the file and a short redacted prefix/suffix.

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