mcp-builder

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The dependencies anthropic and mcp in requirements.txt are from trusted organizations (Anthropic).\n- [COMMAND_EXECUTION] (SAFE): The MCPConnectionStdio class implements standard subprocess-based communication for MCP servers. No malicious or suspicious hardcoded commands were found.\n- [DATA_EXFILTRATION] (SAFE): While the skill implements network-based transports (SSE and HTTP), these are part of the intended Model Context Protocol connectivity and do not contain logic for unauthorized data transmission.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:25 PM