load-pr-comments
Warn
Audited by Snyk on Jun 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The skill’s runtime workflow uses GitHub API/GraphQL (via
gh api graphqlor GitHub MCPget_review_comments) to fetch PR review thread bodies authored by other users (reviewThreads.nodes[].comments.nodes[].body/comments[].body) and then rewrites that free text into.specs/comments/*.md, which is then ingested by downstream agents—this is outsider-authored content entering the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata