[SlowMist Yu Xian: Be cautious of prompt injection attacks when using AI tools] SlowMist founder Yu Xian issued a security reminder, urging users to be vigilant about prompt injection attacks in agentsmd/skillsmd/mcp and similar tools when using AI tools. Relevant 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, each operation requires user confirmation, which may affect usage efficiency.