tubelab-mcp
Pass
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is configured to ingest and analyze untrusted external content from YouTube, creating a potential vector for indirect prompt injection attacks.
- Ingestion points: Processes video transcripts and user comments via tools like
get_video_transcriptandget_video_comments(documented inSKILL.md). - Boundary markers: Lacks explicit delimiters or instructions to the agent to ignore potentially malicious commands embedded in the fetched YouTube content.
- Capability inventory: The agent utilizes the retrieved data to generate analysis reports and filter further results.
- Sanitization: No specific data sanitization or escaping mechanisms are mentioned for the text content retrieved from external sources.
- [EXTERNAL_DOWNLOADS]: The skill instructions involve fetching additional data and assets from external vendor-controlled URLs.
- Documentation: Fetches extended API specifications from
https://tubelab.net/docs/skill.mdto supplement the core instructions. - Media Assets: Instructs the agent to download and review video thumbnails from
https://i.ytimg.com/vi/<id>/mqdefault.jpgandhttps://cdn.tubelab.net/vi/<id>.jpeg.
Audit Metadata