youtube-automation
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, creating a potential attack surface for indirect prompt injection.
- Ingestion points: Data is retrieved from YouTube via tools such as YOUTUBE_SEARCH_YOU_TUBE, YOUTUBE_LIST_COMMENT_THREADS, and YOUTUBE_VIDEO_DETAILS in SKILL.md.
- Boundary markers: The skill instructions do not provide explicit delimiters or warnings to treat fetched content strictly as data, potentially allowing embedded instructions to be followed by the agent.
- Capability inventory: The agent is granted significant write access to the YouTube account, including video uploads, metadata updates, and channel subscriptions.
- Sanitization: No data sanitization or validation protocols are defined for the information ingested from the YouTube API.
Audit Metadata