hot-monitor

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

• Third-party content exposure detected (medium risk: 0.30). The workflow executes search scripts across general web search engines, social feeds, and news platforms (such as Bing, Google, DuckDuckGo, Hacker News, Sogou, Bilibili, Weibo, and Twitter) whose contents are authored by outside users and ingested at runtime.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill utilizes third-party web search scripts that rely on community-maintained APIs and public scraping (such as twitterapi.io), which constitute a common unofficial operational dependency.