transcribe
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill installs and executes a command-line tool named
transcribethat orchestratesyt-dlp,ffmpeg, andPlaywrightto process video URLs via the Bash tool. - [EXTERNAL_DOWNLOADS]: The skill downloads machine learning models from the
mlx-communityorganization on Hugging Face, which is a well-known repository for AI models. - [EXTERNAL_DOWNLOADS]: A local installation script
install.shis executed to set up third-party dependencies such asyt-dlpandPlaywright. - [PROMPT_INJECTION]: The skill processes untrusted transcripts from external video sources, creating a potential surface for indirect prompt injection.
- Ingestion points: Video URLs from YouTube, TikTok, and other platforms processed in
SKILL.md. - Boundary markers: The output uses a markdown template to label metadata and transcript content.
- Capability inventory: Uses the
Bashtool to run the transcription pipeline. - Sanitization: No specific sanitization or filtering of transcript content is documented in the skill instructions.
Audit Metadata