code-review-assist
Augments human code review by summarizing changes, surfacing key review questions, assessing test coverage, and identifying low-risk sections. Use when reviewing a diff, PR, or code snippet as a senior review partner.
85%
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 required runtime workflow is a human-in-the-loop GitHub code-review session that instructs the agent to discover PRs and fetch PR metadata (title/author/description/files-changed count) from GitHub, which can include outsider-authored free text via PR descriptions/comments.
- Repository
stacklok/toolhive
- Revision
bb62674
- 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.