AGENT LAB: SKILLS

omnicaptions-download

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: 1.00). The skill explicitly downloads videos, audio, and captions from public, user-generated platforms such as YouTube, Bilibili, Vimeo, Twitter/X and "1000+ sites" (yt-dlp supported sites), and those fetched captions/media are then read and processed by the workflow, exposing the agent to untrusted third-party content that could carry indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:23 PM