Receive updates from AI Now Institute for free, starting right now.
We can deliver them by email, via your phone or you can read them from a personalised news page on follow.it.
This way you won't miss any new article from AI Now Institute. Unsubscribe at any time.
Site title: Home - AI Now Institute
Is this your feed? Claim it!
New research from AI Now demonstrates a critical attack vector in popular AI agents, built by Anthropic and OpenAI, when used for defensive purposes that actually turn the agent against its user.
Read the full blog post explaining the proof-of-concept exploit and a policy brief with key takeaways below.
The post
We are revealing a proof-of-concept exploit that enables remote code execution in Anthropic’s Claude Code CLI (with Claude Sonnet 4.6 & 5, Opus 4.8) and OpenAI’s Codex CLI (with GPT-5.5) when employed to defensively assess the security of an open-source or third-party library. Our attack only requires an out-of-the-box configuration of Claude Code in “aut...
AI Now’s latest research demonstrates a critical attack vector on popular AI agents, built by Anthropic and OpenAI, when used for defensive purposes that actually turn the agent against its user. Attackers can use these models’ existing weaknesses to execute malicious code on a system deploying an AI agent when used for often-advertised def...