formcarry-automation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [Unverifiable Dependencies] (LOW): The skill requires connecting to an external MCP endpoint at https://rube.app/mcp. This domain is not listed as a trusted source.
- [Indirect Prompt Injection] (LOW): The skill fetches tool schemas and execution plans from the remote server, which could be exploited via indirect injection. Evidence Chain: 1. Ingestion points: Tool schemas retrieved via RUBE_SEARCH_TOOLS. 2. Boundary markers: None. 3. Capability inventory: Tool execution through RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH. 4. Sanitization: None specified for the retrieved tool data.
Audit Metadata