qinghu-pod-pattern-extract

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to ask the user for an API token and then explicitly embed it in a CLI command (qhkit config set --token <密钥>), which exposes the secret value directly through the agent's context and output.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to download and execute Node.js binaries directly from nodejs.org (or its registry.npmmirror.com mirror) during setup/runtime, which constitutes a weak/unknown/suspicious operational dependency.