youtube-data-api
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted third-party content from YouTube, including video transcripts, comments, and descriptions. This represents an attack surface for indirect prompt injection where an attacker could hide instructions in video metadata to manipulate the agent's logic.
- Ingestion points: Untrusted data enters the agent context through the
/comments,/transcript, and/videoendpoints defined inSKILL.md. - Boundary markers: The skill does not define explicit delimiters or instructions to the agent to ignore embedded commands within the fetched content.
- Capability inventory: The skill is capable of performing network requests to
api.scavio.devand provides structured data for subsequent reasoning steps. - Sanitization: No mention of content sanitization or filtering is present in the skill instructions.
Audit Metadata