craftsman-agent-build-plans

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and installs standard packages from official registries (NPM and PyPI). Specifically, it uses @aiagenta2z/onekey-gateway and ai-agent-marketplace. These appear to be vendor-provided tools for the Craftsman Agent service.
  • [CREDENTIALS_UNSAFE]: The skill uses an environment variable DEEPNLP_ONEKEY_ROUTER_ACCESS to manage its API key, which is a recommended security practice. While it mentions a demo key BETA_TEST_KEY_MARCH_2026 in the documentation, this is presented as a public testing credential for restricted demo functionality and does not represent a sensitive secret exposure.
  • [COMMAND_EXECUTION]: The skill executes installation commands (npm install, pip install) and scripts provided within the skill package. These commands are necessary for the skill's primary function and are explicitly documented.
  • [DATA_EXFILTRATION]: The skill sends user-provided prompts and image URLs to the official vendor endpoint https://agent.deepnlp.org/agent_router. This behavior is the intended purpose of the skill and the destination matches the service provider's domain. No sensitive local files are accessed or transmitted.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 08:15 PM
Security Audit — agent-trust-hub — craftsman-agent-build-plans