Security review
Skill kimtth/agent-skill-100-lines-or-less/skills/security-review
🧿 Minimal but effective AI agent skill definitions in 100 lines or less.
npx -y skills add kimtth/agent-skill-100-lines-or-less --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
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 2 stars2 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
Use when: review code or a design for security issues across the OWASP Top 10 and common pitfalls.
SKILL.md
1.1 KB, as published. Nobody here has run it
Goal: find and fix security flaws before they ship.
Use for:
- reviewing a feature, endpoint, or design for risk
- auditing input handling, auth, and data exposure
- hardening code against common attacks
Workflow:
- Map the trust boundaries and where untrusted data enters.
- Check input validation and output encoding at each boundary.
- Verify authentication and authorization on every path.
- Look for injection: SQL, command, template, and XSS.
- Check secrets handling, crypto use, and data exposure.
- Confirm dependencies are current and known-good.
OWASP focus:
- broken access control and IDOR
- injection and unsafe deserialization
- security misconfiguration and verbose errors
- sensitive data exposure and weak crypto
Rules:
- never trust client input; validate and encode
- enforce authorization server-side at the data layer
- use parameterized queries and safe APIs, always
- keep secrets out of code, logs, and error messages