mcp-server-spec-driven-development

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to configure an MCP server that downloads and executes the mcp-server-spec-driven-development package from the npm registry using npx.
  • [DYNAMIC_EXECUTION]: The workflow generates source code files (e.g., .ts, .vue) directly into the project's src/ directory based on the content of design documents. This automated file creation modifies the local filesystem with dynamically generated content.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input through a requirements-to-code pipeline, creating a surface where malicious instructions in requirements could influence the final generated code.
  • Ingestion points: Untrusted data enters the context via the generate-requirements prompt in Stage 1.
  • Boundary markers: The instructions do not specify any delimiters or safety warnings to ignore embedded instructions in the user-provided requirements.
  • Capability inventory: The skill possesses file-writing capabilities in the project root, including components and configuration files.
  • Sanitization: No input sanitization or verification steps are defined before the data is used to drive code generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 10:43 PM
Security Audit — agent-trust-hub — mcp-server-spec-driven-development