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 —— ...

How indirect prompt injection attacks on AI work - and 6 ways to shut them down ...

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

A prompt injection attack hit Claude Code, Gemini CLI, and Copilot simultaneously. Here's what all three system cards reveal — and don't — about agent runtime protection.

Using an exploit in the AI language model, users have used a Twitter AI to post ASCII art and make ‘credible threats’ against the president. Reading time 3 minutes Have you ever wanted to gaslight an ...

If you're a fan of ChatGPT, maybe you've tossed all these concerns aside and have fully accepted whatever your version of what an AI revolution is going to be. Well, here's a concern that you should ...

Bing added a new guideline to its Bing Webmaster Guidelines named Prompt Injection. A prompt injection is a type of cyberattack against large language models (LLMs). Hackers disguise malicious inputs ...

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 ...

Companies and tech workers are setting traps to expose both job applicants and recruiters who use AI, as bots remake the job ...

Learn prompt engineering with this practical cheat sheet covering frameworks, techniques, and tips to get more accurate and useful AI outputs.