gzh-search-crawler

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

• Third-party content exposure detected (low risk: 0.10). The agent skill queries an external search API for WeChat articles based on user keywords and displays/exports the returned article titles, authors, and summaries, representing user-initiated fetching of web search results rather than monitoring an un-vetted input queue.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill makes runtime HTTP requests to an API hosted on redfox.hk during normal execution, constituting an operational third-party dependency with weak provenance.