AAIF新增四个项目，MCP转向安全与身份
原标题：AGNTCon + MCPCon 2026: Agentic AI Foundation Adds Four Projects as MCP Turns to Security
AI 摘要
在2026年AGNTCon + MCPCon北美大会上，Agentic AI Foundation（AAIF）宣布新增四个项目（阿里巴巴的OpenSandbox、OpenAI的Open Responses、Anthropic的Agent Skills、Hugging Face的OpenEnv），使项目总数从三个创始项目增至十个。大会主题从协议新功能转向安全与身份，MCP联合创建者David Soria Parra宣布Claude Code支持MCP任务，可运行数分钟至数天。UC Berkeley教授Dawn Song指出前沿AI短期内更利于攻击者，GPT-5.6 Sol在两小时内对869个目标生成约230个可用漏洞利用。
正文节选
At AGNTCon + MCPCon North America 2026 in San Jose, the Agentic AI Foundation (AAIF) added four projects, taking it from three founding projects to ten in its first year. The October 22-23 event followed PyTorch Conference at the same venue, and much of its program moved from new protocol features to security and identity. Mazin Gilbert, executive director of the AAIF, opened with the project news and three new governance committees. Alibaba contributed OpenSandbox, a secure sandbox for running