pr-review-lite
Reviews a PR in shadow at low cost: a script makes direct, cached model calls over the pr-reviewer's review packet (no harness session, no tools) and compares its findings with the full reviewer's. Writes artifacts only, never to GitHub. Invoke with /pr-review-lite.
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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 reads PR descriptions, comments, and file diffs via GitHub API (`gh api`) and review packets, which include outsider-authored pull request text and existing thread comments.
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 script makes a direct inbound API call to `https://api.anthropic.com/v1/messages` using an arbitrary user-supplied key or environment variable, constituting an unverifiable external runtime dependency with weak provenance.
- Repository
mthines/agent-skills
- Revision
8f81cde
- 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.