Hugging Face
Warn
Audited by Snyk on Apr 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's required discovery and inference workflows (see discovery.md and SKILL.md) explicitly query public Hugging Face APIs (https://huggingface.co/api/models, /api/datasets, /api/spaces and api-inference.huggingface.co) which host user-generated/untrusted models, datasets, and Spaces whose content is read and used to select models and drive subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata