wmp-to-uniapp

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly instructs the agent to read project files (project.config.json) and copy the WeChat appid into generated manifest.json and to write converted files verbatim, which requires the LLM to reproduce values from source files (potentially secrets) in its output.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). Step 1 (“Analyze source project”) ingests outsider-authored free text by reading the user-provided WeChat Mini Program source files (e.g., all pages/ and components/ directories’ .wxml/.js/.wxss and app.json/app.js) from a root path the user supplies, before any “specific item” selection.