AGENT LAB: SKILLS

yt-dlp-downloader

Warn

Audited by Snyk on Feb 15, 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 explicitly accepts arbitrary public video URLs (YouTube, Bilibili, Twitter/X, TikTok, etc.) and runs yt-dlp (see SKILL.md and scripts/download.sh which eval the constructed command and support --write-subs and format listing), causing the agent to fetch and consume untrusted, user-generated web content and metadata from those third‑party sites.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:24 PM