interrogate
Warn
Audited by Snyk on Aug 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow ingests only the user-provided intent/diff/files they point to or from a PR/commit context (Step 1–3), meaning outsider-authored free text can flow into the reviewers’ prompts and thus into the LLM at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata