Skip to content
Back to skills

Security Review Guidance

ASecurity

Use when the user asks to review changes for security vulnerabilities — injection, XSS, auth flaws, secrets, SSRF, unsafe deserialization, path traversal. Delegates to the security-reviewer subagent via /security-review. Triggers on "security review", "check for vulnerabilities", "is this safe", "audit this diff for security", "OWASP".

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 1, 2026
ai-agentsawsgitsecurity

Security analysis

A100/100

Scanned October 1, 2026

npx -y skills add matthews-wong/claude-code-plugins --skill security-review-guidance --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Security Review Guidance?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Security Review Guidance
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/matthews-wong-security-review-guidance/badge)](https://www.skillsdirectory.com/skills/matthews-wong-security-review-guidance)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: security-review-guidance
description: 'Use when the user asks to review changes for security vulnerabilities — injection, XSS, auth flaws, secrets, SSRF, unsafe deserialization, path traversal. Delegates to the security-reviewer subagent via /security-review. Triggers on "security review", "check for vulnerabilities", "is this safe", "audit this diff for security", "OWASP".'
---

# Security review guidance

When the user wants their changes audited for security vulnerabilities — before committing or merging security-relevant code — route it through this plugin.

## When this applies

- The user asks to check a diff or PR for exploitable flaws.
- Changes touch auth, input handling, deserialization, network calls, or secrets.

## What to do

Run `/security-review` (optionally with a git ref or range; defaults to the working diff). It dispatches the read-only `security-reviewer` subagent, which reports severity-ranked, actionable findings (injection, authn/authz, secrets, SSRF, unsafe deserialization, path traversal, and more). Relay the findings.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…