story-short-scan

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly says the browser-cdp flow must extract a Bearer token from Chrome cookies and use it to call backend APIs, which requires the agent to read and handle a secret token directly.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). High-risk: the tooling intentionally extracts an authentication cookie (Admin-Token) from the browser and uses it to call backend APIs via fetch, enabling access to protected data (credential exposure and data exfiltration); the code also executes arbitrary JS in page context via base64-eval which can read cookies and other sensitive page state.

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

• Third-party content exposure detected (medium risk: 0.30). 该技能的运行流程在 browser-cdp 采集模式下会直接打开并解析外部平台页面内容（如点众的 https://www.ishugui.com/browse 及其书籍/简介文本、黑岩的 manage.zhangwenpindu.cn/books/booklist 与详情简介），把其中的自由文本作为样本输入给后续 LLM 分析。