mcp-server-builder
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes Python scripts (openapi_to_mcp.py, mcp_validator.py) designed to be executed via CLI. These tools process input files (OpenAPI specs, manifests) to automate engineering workflows.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted data such as OpenAPI specifications. While this presents an ingestion surface where malicious instructions could be embedded in API metadata (e.g., descriptions), the skill mitigates this by focusing on structural conversion and providing a validator for manual review. * Ingestion points: scripts/openapi_to_mcp.py and scripts/mcp_validator.py (via stdin or --input). * Boundary markers: Not explicitly implemented in generated manifests. * Capability inventory: File system writes for scaffold generation in scripts/openapi_to_mcp.py. * Sanitization: sanitize_tool_name filters non-alphanumeric characters for generated tool names.
- [DYNAMIC_EXECUTION]: The openapi_to_mcp.py utility generates executable Python or TypeScript code based on predefined templates. This behavior is the primary purpose of the skill and provides a starting point for developers to implement their server logic.
Audit Metadata