skills/solvapay/skills/create-mcp-app/Gen Agent Trust Hub

create-mcp-app

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses the create-solvapay package from the npm registry as its core engine for scaffolding projects. It also references standard CLI tools like wrangler and npx for deployment and initialization tasks.
  • [COMMAND_EXECUTION]: Local wrappers (describe.mjs and scaffold.mjs) use spawnSync to execute the business logic contained within the create-solvapay package. This is used to parse user-provided OpenAPI specifications and generate the resulting project files.
  • [DATA_EXFILTRATION]: The skill handles sensitive information including SolvaPay merchant keys and upstream API credentials. It implements robust safeguards such as automatic .gitignore population, warnings against committing .env files, and explicit instructions to use platform-native secret stores (e.g., wrangler secret put).
  • [SAFE]: The describe.mjs script performs network probes against API endpoints defined in user-supplied OpenAPI documents. This is a functional verification step used to confirm the specification targets a reachable server before the project is scaffolded.
  • [SAFE]: The skill employs a series of numbered 'Gates' (G0–G9) that serve as human-in-the-loop confirmation points. These ensure that the user reviews and approves intent clusters, tool schemas, and project configurations before files are written to the local filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 05:39 PM
Security Audit — agent-trust-hub — create-mcp-app