hf-mem
Warn
Audited by Snyk on Oct 27, 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 agent reads model metadata and config/header files from the Hugging Face Hub (an external platform where third parties can publish repositories), making any outsider-authored model configs/metadata an indirect prompt injection source accessed via search/fetch.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata