mcp-builder
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): The skill contains only instructional guidance and does not attempt to bypass agent safety protocols.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or unauthorized network operations are present.
- [Remote Code Execution] (SAFE): The skill references official MCP libraries from trusted sources (Anthropics/Model Context Protocol ecosystem). No arbitrary command execution patterns were found.
- [Obfuscation] (SAFE): No encoded or hidden content was identified.
Audit Metadata