iopho-analyzing-videos

Warn

Audited by Snyk on Feb 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). The skill explicitly ingests and analyzes arbitrary video files (Stage 1: "Video file → Gemini File API") and its docs show combining with iopho-getting-videos to download public videos (e.g., YouTube) so the agent reads/transcribes untrusted, user-generated third-party content as part of its required analysis pipeline, which could embed instructions that influence downstream actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 07:29 PM