Skills
skills/hanli0705/lead_agent/mcp-builder/Gen Agent Trust Hub

mcp-builder

Warn

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [Dynamic Execution] (MEDIUM): The MCPConnectionStdio class in scripts/connections.py uses the stdio_client to execute system commands provided via the command and args parameters. This allows the skill to spawn arbitrary processes on the host system.
  • [Data Exposure & Exfiltration] (LOW): The MCPConnectionSSE and MCPConnectionHTTP classes in scripts/connections.py facilitate network communication with external URLs. This capability enables the agent to connect to remote servers, which could be used for data transmission to non-whitelisted domains if the URL is provided by a user or external source.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 04:06 AM