modelopt-evaluation
Warn
Audited by Snyk on Nov 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow has the agent WebSearch and read arbitrary third-party HuggingFace model cards (author-controlled free text) when choosing sampling, token budgets, and deployment flags, which is a low-risk path because the agent must select the page first.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata