github-review-pr
Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for local uncommitted changes — this skill only reviews pull requests on GitHub.
78
100%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly requires detecting "hardcoded secrets/credentials" and also mandates that every finding include a verbatim quote of offending lines (copied from the diff) and post those findings in review comments or the terminal, which forces the LLM to output secret values if present.
Low
Low-risk findings.
2 low severity findings. 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 workflow’s required runtime reads outsider-authored GitHub PR free text (diff, PR description, commit messages, and PR discussion comments/reviews) via `gh pr diff` and `gh pr view --json comments,reviews`, passing it into multiple subagents as untrusted content.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill issues gh api calls that fetch repository guidance files at runtime (e.g., gh api "repos/OWNER/REPO/contents/AGENTS.md?ref=BASE_SHA" --jq '.content' | base64 -d), and those fetched files are incorporated into subagent prompts and used as authoritative policy, so remote file content can directly control agent behavior.
- Repository
- feiskyer/claude-code-settings
- Commit
45ad30f
- 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.