google-genai
Warn
Audited by Snyk on Feb 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill includes an "Image URLs" example in references/multimodal.md that uses requests.get(...) to download arbitrary images from external HTTPS URLs and then sends those images to the Gemini model for analysis, which clearly ingests untrusted third‑party content that the agent will read/interpret.
Audit Metadata