x-tweet-fetcher

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests public, user-generated content (tweets, replies, user timelines, Weibo/Bilibili/CSDN/WeChat pages and Google search results) as part of its required workflow (see SKILL.md references to scripts/fetch_tweet.py, scripts/fetch_china.py, and camofox_search()/Camofox rendering), so untrusted third-party content can be read and influence analysis or downstream actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill’s advanced features require Camofox and the docs explicitly instruct fetching and running remote code (git clone https://github.com/jo-inc/camofox-browser && npm install && npm start), so the GitHub repo (and associated https://camoufox.com) are runtime external dependencies that result in executing externally fetched code.