mcp-builder

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [Command Execution] (LOW): The MCPConnectionStdio class in scripts/connections.py uses mcp.client.stdio to execute local system commands. This is a core functionality for local tool integration and is used as intended by the protocol.
  • [External Downloads] (LOW): The skill facilitates network connections to external URLs via MCPConnectionSSE and MCPConnectionHTTP in scripts/connections.py. This is standard behavior for remote MCP server integration.
  • [Indirect Prompt Injection] (LOW): The skill ingests untrusted data from external tools, creating a surface for indirect prompt injection. \n
  • Ingestion points: Tool outputs are retrieved via the call_tool method in scripts/connections.py. \n
  • Boundary markers: None implemented in the script to separate tool output from instructions. \n
  • Capability inventory: Subprocess execution and network access are available in the connection classes. \n
  • Sanitization: None; data is returned as raw content objects.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:22 PM