video-understanding

Warn

Audited by Snyk on Jun 21, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.85). The skill downloads a video from a user-supplied <VIDEO_URL> (public web content via yt-dlp), then transcribes the resulting audio into readable text (whisper ... --output_format ...), which is outsider-authored transcript content fed into the agent for summarization/analysis.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 21, 2026, 10:49 PM
Issues
1
Security Audit — snyk — video-understanding