comfy-model-downloader
Warn
Audited by Snyk on May 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's SKILL.md explicitly fetches model files from public third-party sources (Hugging Face and direct HTTP/Civitai links under "Auth And Sources") and those untrusted artifacts are downloaded, validated, and then used by generation workflows, so they can indirectly influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata