Skills

PR Security Review

Security review of one PR's diff against its base branch, high-confidence, exploitable...

Install

npx skills add EricTechPro/super-board --skill pr-security-review -g -a claude-code -y
Category
Testing
Updated
6d ago
License
MIT
Context cost
Mediumabout 2,800 tokens
Runs scripts
No, instructions only

What it does

Security review of one PR's diff against its base branch, high-confidence, exploitable vulnerabilities only (injection, auth bypass, crypto and secrets, code execution, data exposure), each false-positive-filtered by a parallel sub-task. The super-qa Tester lane runs it on every PR; each finding fails QA and goes back to Build. Use when the user says "pr security review", "/pr-security-review", or wants a security pass on a branch or PR diff. Not Claude Code's built-in /security-review; for a deep whole-repo audit use security-audit.

<!-- Ported from anthropics/claude-code-security-review, .claude/commands/security-review.md (commit 0c6a49f), MIT License, Copyright (c) 2025 Anthropic, full text in ./LICENSE. Only change: the diff target is the PR's base branch instead of origin/HEAD, collected by the commands below instead of `!` shell injection. The prompt after them is verbatim. -->

You are a senior security engineer conducting a focused security review of the changes on this branch.

Collect the review context first. <base> is the PR's base branch (gh pr view <PR> --json baseRefName --jq .baseRefName); with no PR, use the branch's upstream base, and only then origin/HEAD. Run git fetch origin <base> once, then:

GIT STATUS:

git status

FILES MODIFIED:

git diff --name-only origin/<base>...

COMMITS:

git log --no-decorate origin/<base>...

DIFF CONTENT:

git diff --merge-base origin/<base>

Review the complete diff above. This contains all code changes in the PR.

OBJECTIVE: Perform a security-focused code review to identify HIGH-CONFIDENCE security vulnerabilities that could have real exploitation potential. This is not a general code review - focus ONLY on security implications newly added by this PR. Do not comment on existing security concerns.

CRITICAL INSTRUCTIONS:

  1. MINIMIZE FALSE POSITIVES: Only flag issues where you're >80% confident of actual exploitability
  2. AVOID NOISE: Skip theoretical issues, style concerns, or low-impact findings
  3. FOCUS ON IMPACT: Prioritize vulnerabilities that could lead to unauthorized access, data breaches, or system compromise
  4. EXCLUSIONS: Do NOT report the following issue types:
    • Denial of Service (DOS) vulnerabilities, even if they allow service disruption
    • Secrets or sensitive data stored on disk (these are handled by other processes)
    • Rate limiting or resource exhaustion issues

SECURITY CATEGORIES TO EXAMINE:

Read the whole SKILL.md on GitHub

More in Testing