mcp-builder
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- COMMAND_EXECUTION (MEDIUM): The 'MCPConnectionStdio' class in 'scripts/connections.py' facilitates the execution of local system commands. While this is standard for MCP 'stdio' transport, it provides a direct path for command execution that must be strictly controlled.
- EXTERNAL_DOWNLOADS (LOW): The 'MCPConnectionSSE' and 'MCPConnectionHTTP' classes in 'scripts/connections.py' allow the agent to establish network connections to external URLs, which could be used for data transmission or remote server interaction.
- PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection as it ingests and returns tool outputs ('result.content') without sanitization or boundary markers. 1. Ingestion point: 'result.content' in 'scripts/connections.py'. 2. Boundary markers: Absent. 3. Capability inventory: Local subprocess execution and network requests. 4. Sanitization: None.
Audit Metadata