Claude Skill: Security Review

Resource overview Purpose
• Skill for auth, authorization, secrets, file uploads, SSRF, injection, rate limits, logging, and dependency risk review.

Recommended SKILL.md contents
• Trigger description explaining when Claude should use the skill.
• Step-by-step procedure for the workflow.
• Required checks before edits or publication.
• Verification command or manual acceptance checklist.
• Links to supporting examples, scripts, or templates when the workflow needs them.

What it helps you do

Use this skill because it adds a structured security pass before shipping risky backend or AI features.

Skills load their full instructions only when used, which keeps normal session context smaller.

A reusable `SKILL.md` gives teams a versioned workflow instead of repeated ad hoc prompts.

Best fit users

security-conscious engineering teams, backend developers, and platform owners.

Teams standardizing AI-assisted delivery across multiple repositories.

Builders who want Claude to apply consistent procedures without repasting instructions.

What to know first

clear threat model, changed files, auth rules, data sensitivity, and deployment environment.

A skill directory such as `.claude/skills/<skill-name>/SKILL.md` or `~/.claude/skills/<skill-name>/SKILL.md`.

A concise frontmatter description so Claude can decide when to load the skill.

Environment needed

repository access, dependency manifests, security policy references, and safe permission to inspect config files.

Claude Code skill support and access to the files or commands the workflow needs.

Any external APIs, MCP servers, credentials, or local runtimes required by the specific workflow.