Security review
AI-agent skills for software engineering — works with Claude Code, Codex, Cursor
npx -y skills add vaibhavsaxena022/skills --skill security-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 23 days oldThe repository was created 23 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Review an endpoint or service for common security flaws. Use when adding or reviewing code that handles auth, user input, or sensitive data. Checks authorization, injection, secrets, and data exposure (OWASP-style).
SKILL.md
1.4 KB, as published. Nobody here has run it
Security Review
Check for the security issues that actually bite services.
Checklist
- AuthN / AuthZ — is the caller authenticated? Is object-level authorization checked (can user A access user B's data — IDOR)?
- Injection — parameterized queries (no string-built SQL), safe deserialization, no command/LDAP injection.
- Input validation — validate and bound all external input; reject unexpected fields.
- Secrets — none hardcoded; loaded from env/secret manager; never logged.
- Data exposure — no sensitive fields or PII in responses or logs.
- Abuse — expensive and auth endpoints are rate-limited.
- Dependencies — flag known-vulnerable libraries.
Output
Findings ranked by severity, each: file:line → risk → fix.
Rules
- Authorization bugs (IDOR) and injection are top priority.
- Never log secrets or PII, even at debug level.