youtube
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the YouTube Data API, including video titles, descriptions, and comments, which can contain untrusted instructions.
- Ingestion points: YouTube API responses retrieved via network requests in SKILL.md.
- Boundary markers: Absent. No delimiters are used to separate API content from agent instructions.
- Capability inventory: The skill performs network requests and modifies YouTube account data (playlists, comments) as shown in SKILL.md.
- Sanitization: Absent. No filtering or validation of external content is documented.
- [EXTERNAL_DOWNLOADS]: Python examples in SKILL.md reference the requests library.
- [COMMAND_EXECUTION]: Documentation provides shell snippets that execute Python scripts for API management.
Audit Metadata