llamaguard
Warn
Audited by Snyk on Oct 8, 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). The skill implements a moderation model (LlamaGuard) designed to evaluate user inputs and outputs for safety violations, which inherently processes untrusted user-submitted text as part of its required input/output filtering workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata