youtube-transcript-extract
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes
npx -y yt-subs, which triggers a download of theyt-subspackage from the npm registry. - [REMOTE_CODE_EXECUTION]: The package downloaded from npm is executed locally to perform the transcript extraction.
- [COMMAND_EXECUTION]: The skill invokes shell commands to run
npxand save the transcript data to the filesystem. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing untrusted data from YouTube videos.
- Ingestion points: Content is retrieved from YouTube titles, descriptions, and subtitles via the
yt-substool. - Boundary markers: No delimiters or safety instructions are used to isolate the external content in the output file
yt-subs.md. - Capability inventory: The environment allows shell command execution and file writing.
- Sanitization: There is no evidence of filtering or escaping logic for the retrieved YouTube data before it is presented to the agent context.
Audit Metadata