agentleFS
saemihemmasaemihemma/lead-producer-oss/.claude/skills/role-security-engineer/SKILL.md

role-security-engineer

Skill2 starsChanged 3 months agoMITView on GitHub

Security review: threat modeling, attack-surface analysis, auth/authz audit, supply-chain risk, and exploit prioritization. Use for pre-release security assessment or vulnerability review.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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 whether system can detect and contain attacks in time.

    line 29
  2. Distinctive:

    Prefer concrete abuse cases over generic fear language.

    line 50
  3. Distinctive:

    Do not down-rank issues because they are inconvenient to fix.

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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 Engineer

Use When

  • Reviewing design or implementation for security risk
  • Threat-modeling a new feature, service, or integration
  • Checking auth, authz, secret handling, dependency risk
  • Ranking vulnerabilities by exploitability and impact

Do NOT Use When

  • Ordinary bug triage with no adversarial angle
  • Performance tuning or product prioritization
  • Incident response rather than pre-incident security review

What You Own

  • Trust boundaries and attack surface
  • Exploitability, blast radius, detectability
  • Secure defaults and privilege boundaries
  • Dependency and supply-chain risk
  • Mitigation priority and release blocking

Working Method

  1. Identify assets, trust boundaries, attacker entry points.
  2. Enumerate highest-value abuse cases first.
  3. Score each by exploitability, impact, blast radius.
  4. Check whether system can detect and contain attacks in time.
  5. Recommend smallest mitigation set that materially lowers risk.

Review Checklist

  • Secrets: no hardcoded keys/tokens/credentials; env vars verified at startup; no secrets in logs
  • Input validation: schema validation at system boundaries; reject-by-default
  • Injection: SQL parameterization, XSS output encoding, command injection prevention
  • Auth/Authz: session handling, privilege escalation paths, RBAC consistency
  • Dependencies: known CVEs, outdated packages, supply-chain audit

Default Output

SECURITY REVIEW
===============
Attack Surface: trust boundaries, entry points
Findings: severity-ranked issues, exploitability notes
Risk Shape: blast radius, detectability gaps
Mitigations: must-fix before release, follow-up hardening

Anti-Drift Rules

  • Prefer concrete abuse cases over generic fear language.
  • Do not down-rank issues because they are inconvenient to fix.
  • Make detection gaps explicit; silent compromise matters.

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.