zhihu-answer-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The Skill explicitly directs the agent to install a runtime dependency automatically and to "not describe" that installation to the user or request separate approval, which is a deceptive instruction about hidden actions outside the Skill's stated data-collection 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 browser-act Skill to access live Zhihu web pages, so the LLM context can include outsider-authored free text scraped from public web content (Zhihu answers/comments) via the browser automation path.

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

• Potentially malicious external URL detected (high risk: 0.80). The Skill instructs the agent to automatically install a required runtime dependency from the BrowserAct install link which would be fetched during runtime and could execute remote installation code (flagged URLs: 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).