XHunt Hot Tweets

从 XHunt 抓取 X/Twitter 热门推文榜单并输出中文摘要与互动数据。用户提到“最火推文/热门帖子/Top20/4小时最火/只要AI/AI最火/给我链接+摘要”等请求时使用。支持 group=global|cn、hours=1|4|24、tag=ai|crypto|全部，并可切换过滤模式（全部/仅AI产...

This skill is instruction-only and appears coherent with its goal of scraping XHunt trends. Before installing, note: (1) it requires network access to https://trends.xhunt.ai and a runtime that supports a browser snapshot or web_fetch; (2) scraping may be subject to the target site's terms of service—ensure you’re allowed to fetch and repost content; (3) the skill may surface political or controversial content depending on mode; (4) the README references a GitHub repo—if you want to audit code, verify that repository and review any code there before cloning. If you want tighter control, restrict the skill’s autonomous invocation or test it in a sandboxed environment first.

Type: OpenClaw Skill Name: xhunt-hot-tweets Version: 2.0.2 The skill is designed to extract trending tweets from `https://trends.xhunt.ai` using `browser` and `web_fetch` tools, as explicitly stated in `SKILL.md`. The instructions are transparent, clearly define the target domain, and specify data extraction and output formatting rules. There is no evidence of prompt injection against the agent, data exfiltration, persistence mechanisms, or any other intentional harmful behavior. While the use of user-controlled parameters in URL construction (e.g., `tag` in `SKILL.md`) could pose a vulnerability if the agent's runtime lacks input sanitization, this is a potential flaw in the execution environment, not an indication of malicious intent within the skill's instructions themselves.