phase-4-api

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an external endpoint at https://api.bkend.ai/mcp for configuring Model Context Protocol (MCP) tools, which is a legitimate part of the described service integration.
  • [COMMAND_EXECUTION]: Documentation includes instructions for using the 'claude mcp add' command to integrate third-party backend services into the agent's environment.
  • [DATA_EXFILTRATION]: Outlines the implementation of standard authentication and identification headers (Authorization, x-project-id, x-environment) for communication with the integrated backend service.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 04:43 PM