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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 20, 2026, 03:21 PM
Issues
1
Security Audit — snyk — adversarial-review