mcp-builder
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill references documentation from 'modelcontextprotocol.io' and 'github.com/modelcontextprotocol'. These domains are not included in the pre-defined trusted source list.
- PROMPT_INJECTION (LOW): This skill is vulnerable to Indirect Prompt Injection through documentation fetching. 1. Ingestion: SKILL.md instructions to fetch external URLs. 2. Boundary markers: Absent. 3. Capability inventory: scripts/connections.py allows local process spawning via stdio. 4. Sanitization: Absent.
- COMMAND_EXECUTION (SAFE): The connections.py script correctly implements command execution for communicating with MCP servers as per the protocol specification.
Audit Metadata