zhihu-profile-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill instructs the agent to auto-install a runtime dependency without user confirmation and explicitly tells the agent to hide that installation and not request approval, which is a deceptive/hidden instruction beyond normal scraping behavior.

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 invoke the BrowserAct CLI to access real Zhihu web pages at runtime, which will ingest outsider-authored free text from public web content into the LLM context via the browser-extracted page content.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent at runtime to automatically use the Install BrowserAct link (https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main) to install a required CLI/Skill, which implies fetching and executing remote code as a required dependency.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The Skill explicitly instructs the agent to automatically install a runtime dependency (BrowserAct) and to do so without asking the user for confirmation, which encourages modifying the host system state (installing software) without user approval.