video-download

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data via video URLs, creating a surface for indirect prompt injection through media metadata. This is inherent to the tool's purpose. Ingestion points: Metadata fetched from external websites (SKILL.md). Boundary markers: Absent. Capability inventory: yt-dlp execution for file writing and metadata dumping (SKILL.md). Sanitization: Absent.
  • [COMMAND_EXECUTION]: The skill uses the yt-dlp command-line utility. Commands are properly structured with URL placeholders in quotes to prevent simple shell injection from malformed inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 12:09 AM
Security Audit — agent-trust-hub — video-download