llamaguard
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill explicitly ingests and classifies arbitrary user-provided messages (see check_input/check_output and the /moderate FastAPI endpoint), so untrusted user-generated content is read and interpreted at runtime, enabling indirect prompt-injection risk.
Audit Metadata