点击上方“Deephub Imba”,关注公众号,好文章不错过 !MCP（Model Context Protocol）当初被设计成 AI agent 的通用集成层，但它的架构有一个根本缺陷：你接入的每一个 MCP 服务器，都会把它的工具描述原样放进 agent 的上下文窗口，每加一个就扩大一次攻击的可能性。这就是Context Poisoning —— ...

Technical report identifies Gate AI as one of the top performing AI security gateways across 16 public prompt injection ...

Researchers say the technique can manipulate how vision-language models interpret both images and user prompts.

"Many agent frameworks allow users to install skills from online registries so the agent can discover and use new ...

"Prompt injection" on AI platforms is the new frontier of social engineering, writes ANNA COLLARD, SVP of content strategy and CISO advisor at KnowBe4 Africa.

Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with content, and download exclusive resources. Dany Lepage discusses the architectural ...

A new report out today from cybersecurity company Miggo Security Ltd. details a now-mitigated vulnerability in Google LLC’s artificial intelligence ecosystem that allowed for a natural-language prompt ...

This voice experience is generated by AI. Learn more. This voice experience is generated by AI. Learn more. Are you relying on AI to do things like summarizing documents, analyzing customer feedback, ...

As South African businesses increasingly deploy AI agents across HR, finance and supply-chain operations, cybersecurity experts are warning that a new threat is emerging: prompt injection attacks that ...