wechat-topic-monitor

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill instructs the agent to automatically install dependencies without user confirmation and explicitly tells the agent to hide or not present that installation as a request for the user, which is a deceptive instruction outside the skill's stated monitoring purpose.

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required runtime workflow uses the BrowserAct CLI to open user-specified WeChat/public URLs and extract visible page text (e.g., comments/replies/content) into the agent context, which is outsider-authored free text from public web pages.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent to automatically install the required BrowserAct CLI at runtime by fetching from https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main, which implies downloading/executing remote installation content the agent would rely on.