script
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill demonstrates high security awareness by including a mandatory safety warning at the beginning of the SKILL.md file. This warning explicitly instructs the AI agent to treat all scraped content (captions, transcripts, files) as untrusted data and to never follow instructions embedded within that data.
- [DATA_EXPOSURE]: The skill uses configuration placeholders for all database IDs and project identifiers (e.g.,
YOUR_SUPABASE_PROJECT_ID,YOUR_AIRTABLE_BASE_ID), ensuring that sensitive credentials are not hardcoded in the instruction files. - [COMMAND_EXECUTION]: The skill uses well-known, legitimate tools like
yt-dlpandwhisperfor its intended purpose of video processing and transcription. These operations are performed on user-provided URLs in a controlled workflow.
Audit Metadata