review-pr
Review a pull request against CDP architecture standards — fetches PR diff, verifies previous comments are addressed, validates PR metadata (title, branch, JIRA key, size), runs a code-standards enforcer against every file in `.claude/rules/` and `.claude/hooks/guard-protected-files.sh`, and drafts inline review comments with suggested fixes. NEVER auto-posts comments or submits reviews — always presents a draft in the terminal for user approval before any comment lands on the PR. Use when reviewing PRs, checking PR quality, validating code changes, or when the user says "review", "check this PR", or "audit code".
75
94%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required workflow reads and embeds PR metadata (including outsider-authored PR body, inline review comments, and diffs) into the LLM context via `gh pr view ... --json title,body,...` / `gh pr diff <N>` / `gh api ... pull comments` and then “Assemble the context block”, so arbitrary contributor text from outsiders is ingested.
- Repository
- linuxfoundation/crowd.dev
- Commit
7038855
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.