llama-cpp
Warn
Audited by Snyk on Sep 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 skill workflow instructs the agent to fetch external model pages and tree APIs from Hugging Face (
https://huggingface.co/), which host public user-authored repositories and metadata.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata