youtube-research
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content from YouTube that could contain adversarial instructions intended to subvert the agent's behavior.\n
- Ingestion points: The skill retrieves video comments, captions, and channel descriptions using tools like
youtube_web_v2_video_commentsandyoutube_web_v2_video_captionsas defined inSKILL.mdandreferences/sandbase-api-map.md.\n - Boundary markers: The instructions do not specify the use of delimiters or defensive prompting to separate user instructions from data retrieved from YouTube.\n
- Capability inventory: The skill primarily uses
sandbase_call_toolto interact with external APIs for search and metadata extraction.\n - Sanitization: There is no mention of content filtering, escaping, or validation of the retrieved text before it is integrated into the agent's context.
Audit Metadata