youtube
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides standard documentation and examples for using the TikHub YouTube Web-V2 API. All external requests are directed to the vendor's own infrastructure (api.tikhub.io), which is consistent with the skill's stated purpose.
- [PROMPT_INJECTION]: The skill exhibits an inherent surface for indirect prompt injection by processing untrusted data from YouTube.
- Ingestion points: Video information, comments, captions, and search results are retrieved from YouTube via TikHub endpoints defined in SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions to treat the ingested external content as data rather than instructions.
- Capability inventory: The skill uses curl to fetch data from the API and hands off results to other processing skills.
- Sanitization: No sanitization or filtering of the content retrieved from YouTube is described in the skill instructions.
Audit Metadata