viral-hook
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill facilitates a video processing workflow using dedicated Pika MCP tools for media analysis, asset uploading, and video generation.
- [SAFE]: The skill demonstrates an indirect prompt injection surface by processing external media analysis and user-provided configuration files.
- Ingestion points: Media analysis output from Step 2 and user-supplied 'brand.md' files.
- Boundary markers: None defined.
- Capability inventory: File upload ('upload_asset') and remote video generation ('generate_viral_hook').
- Sanitization: The skill employs instruction-based filtering, directing the agent to extract only typography directives while ignoring unrelated content.
Audit Metadata