review-response
Warn
Audited by Snyk on Jul 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.86). The workflow explicitly takes “reviewer comments” provided by the user (outsider-authored text from peer reviewers) and has the agent parse/classify them, so those comments become free-form prose in the LLM context (directly via the user-supplied reviewer-comment input).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata