zoho-bigin-automation

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill requires a connection to a third-party MCP endpoint at https://rube.app/mcp. This server provides the toolsets and operational logic for the skill and is not included in the list of trusted external sources.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill fetches tool schemas and 'recommended execution plans' from the remote RUBE_SEARCH_TOOLS endpoint.
  • Ingestion points: Tool slugs, schemas, and execution plans returned by the external Rube MCP service.
  • Boundary markers: Absent; the agent is directed to use the returned information directly for subsequent calls.
  • Capability inventory: RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH provide execution capabilities on the remote target.
  • Sanitization: Absent; the skill does not validate the names or structures of tools returned by the remote service.
  • [REMOTE_CODE_EXECUTION] (MEDIUM): The toolkit includes RUBE_REMOTE_WORKBENCH, which suggests an environment for executing complex tasks or scripts remotely within the Composio/Rube infrastructure.
  • [COMMAND_EXECUTION] (LOW): The skill utilizes RUBE_MULTI_EXECUTE_TOOL to perform operations discovered at runtime, which constitutes dynamic tool invocation based on remote data.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:33 PM