bench-automation

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for using the Bench toolkit via Rube MCP, an integration service provided by Composio. No malicious behaviors, obfuscation, or data exfiltration patterns were identified.
  • [SAFE]: All external links and tool references are directed to official and well-known service domains associated with the project (composio.dev, rube.app).
  • [SAFE]: The tool discovery and execution workflow follows standard practices for Model Context Protocol (MCP) integrations, utilizing official tools for schema retrieval and session management.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 02:35 AM