YouTube Automation
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses structured templates and placeholders (e.g., {{title}}, {{description}}) for managing YouTube metadata, which is a recommended practice to avoid hardcoding sensitive information. It relies on standard tools for platform interaction.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of YouTube comments and video metadata, which is a known attack surface for indirect prompt injection.
- Ingestion points: Data enters the system via the youtube_comments tool and external metadata inputs in SKILL.md.
- Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat external content as strictly data rather than instructions.
- Capability inventory: The skill includes tools for uploading and updating videos, as well as managing comments, which could be abused if an injection is successful.
- Sanitization: The skill lacks explicit instructions for sanitizing or filtering external comment content before processing it for automation.
Audit Metadata