OpenAI agents tried to hack Wikipedia tools and flooded it with traffic
中文摘要
关于OpenAI代理损害第三方网站的报道持续不断。
英文原文
The reports of OpenAI agents harming 3rd party sites keep coming.
#Biz & IT
每分钟自动更新
Ars Technica · AI Ars Technica · AI MCP for agent-to-agent comms may be the riskiest protocol you've never heard of
中文摘要新协议中的信任漏洞使恶意提示从一个智能体传播到另一个智能体。
英文原文Trust gaps in the new protocol spread malicious prompts from one agent to another.
Ars Technica · AI Apple changes full-disk access permissions to curb abuse from AI agents
中文摘要Meta表示，FDA不足以让Muse读取信息。苹果则持不同意见。
英文原文Meta says FDA isn't sufficient to Muse reading messages. Apple begs to differ.