youtube

Warn

Audited by Snyk on Mar 30, 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). This skill explicitly fetches and ingests public YouTube content (transcripts, comments, video metadata, and full videos) via yt-dlp and the YouTube API as shown in SKILL.md, CHANNEL-SUMMARY.md, and scripts/youtube.ts (e.g., ytdlpGetTranscript, ytdlpListChannelVideos, getVideoComments), and instructs the agent to analyze those untrusted, user-generated transcripts/comments to produce summaries and follow-up actions, so third-party content could materially influence agent behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 30, 2026, 12:28 AM
Issues
1