ai-multimodal
Warn
Audited by Snyk on Feb 16, 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 ingests and analyzes arbitrary user-supplied and public media (e.g., "process videos ... YouTube URLs" and the gemini_batch_process.py CLI which accepts stdin/--files for images, audio, video, and PDFs), so the agent will read and interpret untrusted, user-generated third‑party content.
Audit Metadata