kontent-ai-automation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill references an external MCP server at
https://rube.app/mcp. This domain is not in the trusted source list. - [PROMPT_INJECTION] (LOW): The skill utilizes dynamic tool discovery which presents an indirect prompt injection surface (Category 8). Evidence: 1. Ingestion points: Tool discovery output from
RUBE_SEARCH_TOOLS. 2. Boundary markers: Absent. 3. Capability inventory:RUBE_MULTI_EXECUTE_TOOLandRUBE_REMOTE_WORKBENCHprovide execution capabilities. 4. Sanitization: Not explicitly implemented in the workflow.
Audit Metadata