procfu-automation
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed to integrate with the Composio Procfu toolkit, following standard operational procedures for MCP (Model Context Protocol) servers.
- [EXTERNAL_DOWNLOADS]: Fetches tool schemas, input definitions, and execution plans from the Rube MCP server endpoint. These resources are part of the intended functionality provided by a well-known service.
- [PROMPT_INJECTION]: The skill processes external data (tool schemas and execution plans) retrieved via discovery tools. While this constitutes an attack surface for indirect prompt injection, it is managed through the platform's tool calling infrastructure and originates from a recognized technology provider.
- Ingestion points: Tool metadata and execution plans returned by RUBE_SEARCH_TOOLS.
- Boundary markers: None explicitly defined in the skill instructions.
- Capability inventory: Includes the ability to manage connections and execute multiple tool calls sequentially via RUBE_MULTI_EXECUTE_TOOL.
- Sanitization: Relies on the underlying MCP implementation for parameter validation.
Audit Metadata