mcp-builder

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The connections.py script includes the MCPConnectionStdio class which executes local commands to initialize MCP servers. While this is the standard mechanism for the Model Context Protocol, providing an execution wrapper is a capability that requires careful handling to prevent arbitrary command injection if the input strings are influenced by untrusted data.\n- [EXTERNAL_DOWNLOADS] (SAFE): The skill directs the agent to fetch documentation from modelcontextprotocol.io and raw.githubusercontent.com. These are legitimate project sources and the downloads are for informational markdown content rather than executable scripts.\n- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection surface identified due to the ingestion of external documentation without safety boundaries.\n
  • Ingestion points: SKILL.md instructions to fetch markdown documentation from external protocol websites and GitHub repositories.\n
  • Boundary markers: None. The skill does not implement delimiters or warnings to ignore instructions within the fetched markdown.\n
  • Capability inventory: The supporting connections.py script provides functionality for subprocess execution (stdio) and network communication (HTTP/SSE).\n
  • Sanitization: None observed in the provided codebase.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 05:28 AM