import-model
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 (low risk: 0.10). The required workflow instructs the agent to fetch configuration and modeling code from the Hugging Face Hub (via Python commands or helper scripts referencing Hugging Face repositories), which represents low-risk ingestion of external repository-hosted text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata