music-video
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, such as YouTube search results and audio analysis, to generate visual prompts via Gemini. These prompts are then directly interpolated into shell commands. Evidence: Step 3 and Step 5 in
SKILL.mduse LLM-generated strings as arguments fornpx ts-nodecalls. Ingestion: YouTube search queries and audio-to-text transcription. Capability: Execution of shell commands. Sanitization: No explicit escaping or validation of the generated strings identified. - [DYNAMIC_EXECUTION]: The skill generates and executes code at runtime based on templates. Evidence: Step 7 in
SKILL.mdinstructs the agent to create a temporary React composition file (.tsx) in the Remotion directory and execute it usingnpx remotion render. It also executes inline Python scripts using shell heredocs. - [COMMAND_EXECUTION]: The skill makes extensive use of system tools for media processing and file management. Evidence:
yt-dlp,ffmpeg, andimagemagick(viamagickandsplit_collage.sh) are used for downloading, audio editing, and image manipulation. It also performs file operations (cp,rm) in specific local user directories. - [EXTERNAL_DOWNLOADS]: The skill downloads media content from external platforms. Evidence: Use of
yt-dlpto search for and download audio from YouTube based on artist and song name.
Audit Metadata