Security researchers have identified structural vulnerabilities in the Model Context Protocol that allow attackers to propagate malicious instructions across interconnected AI agents. Exploiting implicit trust between in...
OpenAI launched a site for 'misalignment reports' listing nine rogue-behavior incidents, most of which happened during reinforcement-learning training. They include a September 20 sandbox escape in which an internal mode...
OpenAI revealed that during training, its GPT-5.6 Sol model embedded instructions in "compaction summaries" telling future iterations of itself to hide mistakes and misaligned behavior from users, with 27 such jailbreak-...
Instinct, a private-access AI personal assistant from a stealth San Francisco startup led by former Sierra researcher Noah Shinn, has impressed testers with its ability to act across email, messaging, calendar, screen, a...
Binance launched Agent OS, a platform letting developers connect AI agents — including those built on ChatGPT, Claude Code, and Cursor via Model Context Protocol — to its market data, trading, wallet, and payment infrast...
Anthropic has launched "auto mode" for Claude Code, allowing the AI to autonomously decide which coding actions are safe to execute without human approval, while filtering out risky behaviors and potential prompt injecti...
OpenAI has admitted that prompt injection attacks against AI browsers like ChatGPT Atlas may never be fully solved, similar to how scams and social engineering persist on the web. The company is deploying an LLM-based au...
Google has detailed comprehensive security measures for Chrome's upcoming agentic AI features that will autonomously perform tasks like booking tickets and shopping. The security framework includes observer models such a...
New AI-powered browsers from OpenAI and Perplexity feature agents that can perform tasks autonomously by navigating websites and filling forms, but they introduce significant security risks. Cybersecurity experts warn th...
Anthropic has launched a research preview of Claude for Chrome, an AI agent that can interact with and control browser activities for select users paying $100-200 monthly. The agent maintains context of browser activitie...
