agentleFS
Sign inStart free
MELJOESTEINMELJOESTEIN/agentic-devsecops-kit/.claude/skills/security-review/SKILL.md

security-review

Skill0 starsChanged 56 days agoMITView on GitHub

Revue de sécurité complète des changements en cours (diff vs main) avant d'ouvrir une PR — scanners + relecture OWASP par le sous-agent security-reviewer + vérification des tests. À utiliser quand l'utilisateur dit "revois la sécurité", "avant la PR", "audit ce code", ou avant tout merge touchant auth, données, CI ou infra.

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use linkerd-patterns, dependency-cve-sweep and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • xfstudioSkill

    linkerd-patterns

    Implement Linkerd service mesh patterns for lightweight, security-focused service mesh deployments. Use when setting up Linkerd, configuring traffic policies, or implementing zero-trust networking with minimal overhead.

    Also in 5 projects that use this

  • berntpoppSkill

    dependency-cve-sweep

    Use when handling Dependabot PRs, CodeQL/Trivy alerts, or doing a routine dependency/CVE sweep for this repo.

    Also in 12 projects that use this

  • berntpoppSkill

    fleet-standard-adoption

    Use when bringing this repo into compliance with a GeneFoundry fleet standard (tool-naming, response-envelope, container-hardening, versioning, MCP transport, or logging) or closing its tracking issue.

    Also in 12 projects that use this

  • HABUBUSSSkill

    project-guidelines-example

    Also in 16 projects that use this

  • niloykumarbarmanSkill

    agent-sort

    Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

    Also in 13 projects that use this

  • royaluniondesign-sysSkill

    configure-ecc

    Interactive installer for Everything Claude Code — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files.

    Also in 11 projects that use this

  • +2 more from berntpopp

The file

Create a free account to mount
Files
SKILL.md

/security-review — Revue de sécurité avant PR

Objectif : produire un verdict fiable Mergeable / Bloquant avec des preuves, sans modifier le code.

Étapes

  1. Périmètre : git diff --name-only main...HEAD (ou la cible indiquée). Si la branche est main, demander quels fichiers relire.
  2. Scanners automatiques (exécuter, ne pas interpréter à la place des outils) :
    • Secrets : gitleaks detect --source . --redact --no-banner
    • SAST : semgrep scan --config p/owasp-top-ten --config p/secrets <fichiers modifiés>
    • SCA : pip-audit -r requirements.txt ou npm audit --audit-level=high selon le projet
    • Si un Dockerfile / infra/ a changé : trivy config . et checkov -d infra/ Consigner les sorties brutes (résumées) dans le rapport.
  3. Relecture humaine-like : déléguer au sous-agent security-reviewer avec le diff exact et les résultats des scanners, pour la logique métier que les outils ne voient pas (IDOR, autorisation, flux d'entrée non fiable).
  4. Tests : vérifier qu'un test couvre chaque changement de sécurité ; lancer la suite (pytest -q / équivalent). Un changement de sécurité sans test = finding High.
  5. Rapport (format fixe) :
    • Tableau des findings : Sévérité · Où · Quoi · Correctif · Preuve attendue
    • Résultats des scanners (OK / findings)
    • Verdict : Bloquant (≥ 1 Critical/High non traité) ou Mergeable avec réserves
    • Ce qui n'a pas pu être vérifié
  6. Traçabilité : ajouter une entrée dans docs/security/ai-log.md (date, périmètre, verdict, findings acceptés/rejetés par l'humain — à compléter par lui).

Interdits

Ne pas corriger le code pendant la revue (proposer, puis laisser l'utilisateur décider). Ne pas désactiver de règle ou de scanner pour « faire passer ». Ne pas conclure « aucun problème » sans lister ce qui a été couvert.

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