Claude Skill

code-security

Review code security, threat-model designs, and vet third-party skills; scan secrets and vulnerabilities with Gitleaks and Trivy.

LLM Mart · 0 points · 2 views 0 listing impressions 0 install-command copies
Download fmind-dot-skills_code-security-3bbe830.zip · 20 KB

Install

skills CLI npx skills add https://github.com/fmind/dot/tree/main/skills/code-security
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install fmind-dot@llmmart
Git git clone https://github.com/fmind/dot.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole fmind/dot collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Code Security

Investigate and fix security defects with verified evidence—scanners inform reasoning, never replace it. Named code-security to avoid colliding with Claude Code and Copilot CLI's built-in security-review command.

Workflow

Read only the matching guide and its required resources.

Task guides

  • ai-red-team: Red-team AI apps and agents with PyRIT: prompt injection, tool misuse, and agent authority.
  • betterleaks: Scan the working tree and history for secrets; handle confirmed exposure.
  • code-review: Assess code and repository security; verify findings and repairs.
  • skill-security-review: Review third-party skills and agent extensions for supply-chain risk.
  • sonarqube: Inspect SonarQube quality gates and issues, run local scans, and gate server-side AI actions with sonar.
  • threat-model: Model attack paths, trust boundaries, abuse cases, and controls.
  • trivy: Scan dependencies, IaC, images, and licenses; generate SBOMs.
Files (dot)
  • references
    • ai-red-team
      • references
        • attack-cases.md 3.8 KB
          Loading…
        • pyrit.md 3.1 KB
          Loading…
      • templates
        • assessment.md 1.9 KB
          Loading…
      • GUIDE.md 2.6 KB
        Loading…
    • code-review
      • references
        • installed-tools.md 988 B
          Loading…
        • ssrf-egress.md 2.9 KB
          Loading…
      • GUIDE.md 4.2 KB
        Loading…
    • skill-security-review
      • references
        • scanners.md 1.1 KB
          Loading…
      • GUIDE.md 4.6 KB
        Loading…
    • trivy
      • references
        • unfixed-report.md 410 B
          Loading…
      • GUIDE.md 3.5 KB
        Loading…
    • betterleaks.md 3.2 KB
      Loading…
    • sonarqube.md 2.9 KB
      Loading…
    • threat-model.md 1.9 KB
      Loading…
  • SKILL.md 1.6 KB
    ---
    name: code-security
    description: "Review code security, threat-model designs, vet skills, red-team AI with PyRIT, and scan with Betterleaks, Trivy, and SonarQube."
    license: MIT
    metadata:
      kind: collection
      author: Médéric HURIER (Fmind)
      source: github.com/fmind/dot/tree/main/skills/code-security
      created: "2026-07-04"
      updated: "2026-11-11"
    ---
    
    # Code Security
    
    Investigate and fix security defects with verified evidence—scanners inform reasoning, never replace it. Named `code-security` to avoid colliding with Claude Code and Copilot CLI's built-in `security-review` command.
    
    ## Workflow
    
    Read only the matching guide and its required resources.
    
    ## Task guides
    
    <!-- guides:start -->
    
    - [ai-red-team](references/ai-red-team/GUIDE.md): Red-team AI apps and agents with PyRIT: prompt injection, tool misuse, and agent authority.
    - [betterleaks](references/betterleaks.md): Scan the working tree and history for secrets; handle confirmed exposure.
    - [code-review](references/code-review/GUIDE.md): Assess code and repository security; verify findings and repairs.
    - [skill-security-review](references/skill-security-review/GUIDE.md): Review third-party skills and agent extensions for supply-chain risk.
    - [sonarqube](references/sonarqube.md): Inspect SonarQube quality gates and issues, run local scans, and gate server-side AI actions with sonar.
    - [threat-model](references/threat-model.md): Model attack paths, trust boundaries, abuse cases, and controls.
    - [trivy](references/trivy/GUIDE.md): Scan dependencies, IaC, images, and licenses; generate SBOMs.
    
    <!-- guides:end -->
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.