playlet-wechat-feed

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs users to verify the API key with commands that print it (echo %REDFOX_API_KEY% / echo $REDFOX_API_KEY) and exposes a --api-key CLI flag (which encourages embedding the key on the command line), meaning an agent could be asked to handle or output the secret verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). 运行时在 assets/daily_report.py 的 fetch_playlet_data() 里通过 POST 到 https://redfox.hk/story/api/parseWork/queryPlayletMsgs 拉取文章列表后，直接把返回字段（如 item["title"]、item["author"]/verifyName/accountName、coverUrl、url）用于生成 HTML 报告，因此外部可在该数据源中投毒的自由文本会被脚本读取并渲染。