quaderno-automation

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill connects to an external MCP server hosted at https://rube.app/mcp. This is the documented endpoint for the Composio toolkit platform, which is a recognized service for AI agent integrations.
  • [SAFE]: The workflow utilizes dynamic tool discovery to retrieve capabilities from the remote server via the RUBE_SEARCH_TOOLS command.
  • [SAFE]: Indirect injection analysis: Ingestion point: RUBE_SEARCH_TOOLS response; Boundary markers: Absent; Capability inventory: RUBE_MULTI_EXECUTE_TOOL (SKILL.md); Sanitization: Relies on the service provider's internal schema validation and the MCP protocol's structured data enforcement.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:38 AM