video-ideation
Pass
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, specifically YouTube video metadata and channel information retrieved via the TubeLab MCP.
- Ingestion points: Data is retrieved through search queries and analysis tools like
reverse-engineer-nicheandreverse-engineer-channelas described inSKILL.md. - Boundary markers: There are no explicit delimiters or instructions to ignore potential embedded commands within the processed data.
- Capability inventory: The agent's actions are restricted to searching, data analysis, and output formatting for video ideation.
- Sanitization: No specific input sanitization or validation logic is defined to filter malicious content that might be present in video titles or descriptions, though a quality filter for "low-effort" videos is mentioned.
Audit Metadata