iopho-analyzing-videos

Warn

Audited by Snyk on Mar 27, 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). This skill uploads and analyzes arbitrary video files (including public/user-generated sources — e.g., the SKILL.md "Combine with Other iopho Skills" example that downloads from YouTube and the Tips line about .info.json from iopho-getting-videos) to the Gemini model (see scripts/video_to_storyboard.py upload_and analyze steps), then parses the model's output to drive frame extraction and downstream actions, so untrusted third‑party content can indirectly influence tool use.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 27, 2026, 04:33 AM
Issues
1