adversarial-review
Warn
Audited by Snyk on Aug 20, 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 adversarial-review workflow, runtime outsider-authored free text can be ingested via the user’s prompt that is used to derive the “intent” and is then embedded into reviewer prompts (Step 2 and Step 3: the reviewers’ template fills {INTENT} from the user message).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata