vero-automation

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an external MCP server at https://rube.app/mcp which is the required endpoint for the Vero toolkit automation as documented by the vendor.\n- [COMMAND_EXECUTION]: The skill describes the use of RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH to perform automation operations on the Vero platform, which is consistent with its intended functionality.\n- [PROMPT_INJECTION]: The skill interacts with an external data source that could serve as an indirect injection surface.\n
  • Ingestion points: Dynamic tool schemas retrieved via RUBE_SEARCH_TOOLS from https://rube.app/mcp.\n
  • Boundary markers: Absent; the agent is instructed to use the tool definitions as provided by the server.\n
  • Capability inventory: Tool execution through RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH.\n
  • Sanitization: Absent; the process relies on the vendor-controlled MCP server for safe schema delivery.\n- [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. The skill follows standard practices for integrating with the Composio MCP ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 07:09 AM