Cline CLI 2.3.0 was published with a stolen npm token, installing OpenClaw in an 8-hour attack affecting ~4,000 downloads.

While the AI itself wasn’t weaponized, the technique raises concerns about AI agents with broad system access.

This voice experience is generated by AI. Learn more. This voice experience is generated by AI. Learn more. Prompt injection attacks can manipulate AI behavior in ways that traditional cybersecurity ...

Why the first AI-orchestrated espionage campaign changes the agent security conversation Provided byProtegrity From the Gemini Calendar prompt-injection attack of 2026 to the September 2025 ...

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 ...

Technical details and a public exploit have been published for a critical vulnerability affecting Fortinet's Security Information and Event Management (SIEM) solution that could be leveraged by a ...

There’s a well-worn pattern in the development of AI chatbots. Researchers discover a vulnerability and exploit it to do something bad. The platform introduces a guardrail that stops the attack from ...

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 ...

Around 27,000 homes in Berlin are still without power for a fourth day after an arson attack produced the second major blackout since September. It’s taking contractors longer than usual to fix the ...

A new report out today from artificial intelligence security startup Cyata Security Ltd. details a recently uncovered critical vulnerability on langchain-core, the foundational library behind ...

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 ...

OpenAI built an "automated attacker" to test Atlas' defenses. The qualities that make agents useful also make them vulnerable. AI security will be a game of cat and mouse for a long time. OpenAI is ...