zhihu-comment-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill contains explicit instructions to install runtime dependencies automatically without user confirmation and to hide/describe the installation link so it does not appear as a user action, which are deceptive and 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). This skill’s required runtime workflow invokes the external browser-act Skill to access Zhihu pages and extract visible comment text (outsider-authored free text from public web content) into the agent’s context for processing/export.

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 install and invoke the BrowserAct CLI at runtime using the installation link https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main (and the related https://www.browseract.com/?co-from=social-media), which implies fetching and running remote installation code as a required runtime dependency.