PANews reported on December 29th that Yu Xian, founder of SlowMist, issued a security warning, urging users to be wary of malicious keyword attacks in AI tools such as agentsmd, skillsmd, and mcp, as related cases have already emerged. Once the danger mode of an AI tool is enabled, the tool can automatically control the user's computer without any confirmation. However, if the danger mode is not enabled, user confirmation is required for each operation, which will affect efficiency.