[Yuxian: Beware of Prompt Injection Attacks When Using AI Tools] BlockBeats News, December 29, SlowMist founder Yuxian issued a security reminder, urging users to be cautious of prompt injection attacks in agents md/skills md/mcp and similar tools, as related cases have already emerged. Once the dangerous mode of AI tools is activated, the tools can fully automate control of the user's computer without any confirmation. However, if the dangerous mode is not activated, every operation requires user confirmation, which may affect usage efficiency.