wechat-search-results-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The Skill explicitly instructs the agent to install BrowserAct automatically "without asking the user to confirm" and to "not describe" that installation or request approval, which is a hidden/deceptive instruction outside the skill's 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 live public WeChat pages and extract visible comment/article text at runtime, which is outsider-authored free text from public web content.

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

• Potentially malicious external URL detected (high risk: 0.90). The Skill instructs the agent to automatically use the "Install BrowserAct" link at runtime to obtain a required CLI/Skill (which implies fetching and installing remote code), specifically via https://www.browseract.com/?co-from=social-media and https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main, so the URLs are used at runtime to obtain/execute external code.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The skill instructs the agent to automatically install the BrowserAct dependency and resume execution without requesting user approval, which directs the agent to modify the host system state (install software) even though it does not explicitly request sudo, edit system files, or create users.