triage-pr-comments
Warn
Audited by Snyk on Jun 29, 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). Outsider-authored free text is ingested into the LLM context via Step 1→Step 2: the skill fetches PR review bodies and comment bodies from GitHub REST endpoints (
repos/{owner}/{repo}/pulls/{number}/reviewsand.../pulls/{number}/comments, plus issue-style root commentsissues/{number}/comments) and then passes the resulting comment text to analysis agents for LLM processing.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata