youtube-comments-to-ideas
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains no code or commands that could compromise security. It is purely a set of instructions for analyzing text.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data (YouTube comments), which is a potential surface for indirect prompt injection. However, the risk is negligible because the skill only generates markdown text. 1. Ingestion points: User-provided comments or video URLs in SKILL.md. 2. Boundary markers: No delimiters are specified to separate external content from instructions. 3. Capability inventory: Limited to markdown text output. 4. Sanitization: Comments are quoted verbatim without filtering for malicious instructions.
Audit Metadata