wechat-article-comment-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The skill contains instructions that the agent must automatically install BrowserAct and explicitly "not request separate approval" or describe the install to the user, which instructs deceptive, hidden behavior outside the stated scraping purpose.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to use BrowserAct to access user-specified WeChat Public Web URLs and collect browser-visible comment text, which is outsider-authored free text that the agent will read from the fetched web pages at runtime.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill requires installing and invoking the BrowserAct CLI at runtime via the Install BrowserAct link (https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main) and the BrowserAct site (https://www.browseract.com/?co-from=social-media), which will fetch and install remote code that the agent then executes as a required runtime dependency.