video-download

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process metadata from external URLs provided at runtime.
  • Ingestion points: Data returned by yt-dlp --dump-json (such as video titles, descriptions, and comments) or metadata embedded in downloaded files.
  • Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the fetched metadata.
  • Capability inventory: The skill utilizes subprocess execution to run yt-dlp and ffmpeg, and it performs file system write operations to save downloads.
  • Sanitization: No sanitization or validation of the fetched metadata is mentioned before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing yt-dlp and ffmpeg via standard package managers like pip, apt, or Homebrew. These are well-known tools and registries used for media processing.
  • [COMMAND_EXECUTION]: The skill relies on executing shell commands for yt-dlp and ffmpeg to download and process media files. This behavior is consistent with the primary purpose of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 08:42 AM