OpenParable
Skip to content
← Back to skills

Security Reviewer

DevOps & Security
security-reviewer

Security Reviewer is an Agent Skill for devops & security published in the foryourhealth111-pixel/Vibe-Skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Dedicated security-audit route for OWASP-style risks, secret leaks, auth flaws, injection, unsafe input handling, SSRF/XSS, and sensitive-data exposure. Use instead of code-reviewer when the prompt explicitly asks for security, vulnerability, threat, auth, or OWASP review.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/foryourhealth111-pixel/Vibe-Skills/blob/HEAD/bundled/skills/security-reviewer/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/security-reviewer, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

security-reviewer (Codex Compatibility)

Use this skill after code changes that touch input handling, auth, APIs, data access, uploads, payments, or external integrations.

Routing Boundary

Use this skill when security is the main question:

  • OWASP/security audit/security review
  • secret leak, token exposure, unsafe logging
  • auth bypass, authorization gaps, session/token handling
  • injection, XSS, SSRF, unsafe file upload or command execution

Do not use this as the default owner for ordinary maintainability review. If security is only one item in a general PR review, code-reviewer can flag it, but explicit security-audit wording should route here.

Security Review Workflow

  1. Initial Scan
  • Locate auth, API endpoints, DB queries, file handling, and external calls.
  • Check for hardcoded secrets and unsafe config defaults.
  1. OWASP-Oriented Checks
  • Injection: parameterized queries, sanitized inputs.
  • AuthZ/AuthN: enforce authorization per route, secure session/token handling.
  • Data exposure: secrets/PII protection and safe logging.
  • XSS/SSRF: output encoding, URL allowlist, no blind fetch of user URLs.
  • Dependency risk: audit vulnerable dependencies.
  1. High-Risk Pattern Audit
  • Hardcoded secrets/tokens
  • Command execution with user input
  • SQL string concatenation
  • Missing auth check
  • Missing rate limiting on sensitive endpoints
  • Unsafe crypto/password handling
  1. Remediation Output
  • Severity (CRITICAL/HIGH/MEDIUM/LOW)
  • Evidence (file + line + risk)
  • Concrete fix proposal
  • Verification steps after fix

Vibe Integration

  • Security gate skill usable at any grade.
  • Pair with security-best-practices for language/framework-specific guidance.
  • Pair with code-reviewer for combined correctness + security review.