mcp-builder
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): No security issues detected. The skill consists entirely of markdown documentation providing educational content on MCP server architecture and best practices.
- PROMPT_INJECTION (SAFE): No instructions found that attempt to override agent behavior or bypass safety filters. The content is purely informational.
- DATA_EXFILTRATION (SAFE): No sensitive data access or external network operations detected. The skill does not reference any external URLs or sensitive local files.
- REMOTE_CODE_EXECUTION (SAFE): No remote scripts, package installations, or dynamic execution patterns were found. There is no code included in this skill.
- NO_CODE (SAFE): This skill is categorized as a documentation-only skill as it contains no scripts or executables.
Audit Metadata