comfyui-core
Warn
Audited by Snyk on Apr 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly tells the agent to proactively search and download models from public third-party sources (HuggingFace and CivitAI via their APIs) when a model is missing, so the agent ingests external, community-hosted content that can directly influence model selection and subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata