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: 0.90). Yes — the skill explicitly ingests and analyzes untrusted public/user-generated content (e.g., YouTube URLs in references/video-analysis.md via types.Part.from_uri and arbitrary user files/URLs handled by the gemini_batch_process.py CLI --files/--reference-images and inline URI/file upload flows), so the agent will read and interpret third-party content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 07:26 AM