ai-multimodal

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: 0.90). The skill accepts and processes public web content (e.g., YouTube videos and public image URLs) — see references/video-analysis.md (YouTube URL processing with types.Part.from_uri) and references/vision-understanding.md (URL (Public Images) example) — meaning the agent will fetch and interpret untrusted, user-generated third-party content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 07:39 AM