proofly-automation
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or safety bypass instructions were identified in the skill code or metadata.
- [EXTERNAL_DOWNLOADS]: Retrieves tool schemas and execution plans from the Rube MCP endpoint (rube.app/mcp) and references official Composio documentation (composio.dev). These are established endpoints for the service.
- [COMMAND_EXECUTION]: Executes automation tasks through tools such as RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH. These operations are performed within the context of user-authorized toolkit connections.
- [PROMPT_INJECTION]: The skill is designed to ingest and follow recommended execution plans and pitfalls from a remote tool discovery service. Ingestion point: RUBE_SEARCH_TOOLS output. Boundary markers: None. Capability inventory: RUBE_MULTI_EXECUTE_TOOL, RUBE_REMOTE_WORKBENCH. Sanitization: None. This surface is a functional requirement for dynamic tool discovery in the Composio ecosystem.
Audit Metadata