dsl-vm-reverse

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.95). The skill explicitly instructs extracting runtime tokens (e.g., calling getToken, capturing sessionId + sig and intercepting API requests), which requires handling and likely outputting secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). High risk — the skill explicitly documents how to bypass browser anti-detection, inject into/execute obfuscated JS VM at runtime, and extract browser-bound tokens (getToken), which facilitates credential/token theft and abuse.

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

• Third-party content exposure detected (low risk: 0.10). SKILL 的“通用逆向工作流/运行时注入（方案B）”会在 Phase 6 通过 Playwright page.goto('https://target-page.com') 进入目标网页并在页面上下文中等待/读取 window.AWSCInner，因此会摄取网页端由外部作者（被访问站点内容）提供的可读文本/脚本。