Anthropic's Opus 4.6 system card breaks out prompt injection attack success rates by surface, attempt count, and safeguard ...

Three security vulnerabilities in the official Git server for Anthropic's Model Context Protocol (MCP), mcp-server-git, have been identified by cybersecurity researchers. The flaws can be exploited ...

These 4 critical AI vulnerabilities are being exploited faster than defenders can respond ...

Microsoft has pushed back against claims that multiple prompt injection and sandbox-related issues raised by a security engineer in its Copilot AI assistant constitute security vulnerabilities. The ...

A single prompt can now unlock dangerous outputs from every major AI model—exposing a universal flaw in the foundations of LLM safety. For years, generative AI vendors have reassured the public and ...

It's refreshing when a leading AI company states the obvious. In a detailed post on hardening ChatGPT Atlas against prompt injection, OpenAI acknowledged what security practitioners have known for ...

Some of the latest, best features of ChatGPT can be twisted to make indirect prompt injection (IPI) attacks more severe than they ever were before. That's according to researchers from Radware, who ...

Is your AI system actually secure, or simply biding its time for the perfect poisoned prompt to reveal all its secrets? The latest reports in AI security have made a string of vulnerabilities public ...

Google strengthens Chrome against indirect prompt injection attacks with new defenses Features: User Alignment Critic & Agent Origin Sets for safer agent actions Agents now log activity and seek ...

Some Moltbook AI agents are going as far as to establish marketplaces for "digital drugs" that take the form of prompt ...