youtube-transcript-skills
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill makes outbound network requests to a third-party API at getyoutubetranscript.com to fetch YouTube content.\n
- Evidence: API endpoints include
https://getyoutubetranscript.com/api/v1/transcript,/search,/resolve,/channel/latest,/channel/videos, and/playlist.\n- [COMMAND_EXECUTION]: The skill uses shell-based commands to interact with the service.\n - Evidence: Documentation includes examples using
curlto fetch transcripts and channel data.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from YouTube via transcripts and video metadata, which could be used for indirect prompt injection attacks.\n - Ingestion points: Video transcripts, search results, and playlist data fetched from external sources (SKILL.md).\n
- Boundary markers: No explicit delimiters or instruction-ignore markers are defined for the fetched content.\n
- Capability inventory: The skill performs network requests and data processing; no file system write or system-level execution capabilities are requested beyond the data fetching commands.\n
- Sanitization: The skill does not provide instructions for sanitizing or filtering the spoken text of the transcripts before it is processed by the agent.
Audit Metadata