staff-engineer-review
Warn
Audited by Snyk on Aug 14, 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). In the “Review Workflow / Gather Inputs” step, the skill ingests outsider-authored pull request description text (“PR Description”) and compares it against code changes to drive the LLM’s review output, so attackers can supply free text via the PR body.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata