pr-fix
Warn
Audited by Snyk on Jul 7, 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). Yes—Step 2 ingests outsider-authored PR review comments/bodies and issue comments via GitHub GraphQL (
reviewThreads/comments/reviews.nodes[].body) and Step 3 explicitly treats those comment bodies as untrusted input, which would be fed into the agent’s LLM context for classification and planning.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata