SlowMist founder Yu Xian issued a security warning. When using AI tools, users must be vigilant against prompt injection attacks in agentsmd/skillsmd/mcp and other places. Related cases have already appeared. Once the dangerous mode of AI tools is enabled, the related tools can fully control the user's computer automatically without any confirmation. However, if the dangerous mode is not enabled, each operation requires user confirmation, which will also affect usage efficiency.
All Comments