Researchers have found a Google Calendar vulnerability in which a prompt injection into Gemini exposed private data.

There’s a well-worn pattern in the development of AI chatbots. Researchers discover a vulnerability and exploit it to do ...

CrowdStrike's 2025 data shows attackers breach AI systems in 51 seconds. Field CISOs reveal how inference security platforms ...

Varonis found a “Reprompt” attack that let a single link hijack Microsoft Copilot Personal sessions and exfiltrate data; Microsoft patched it in January 2026.

Agent-based AI systems promise productivity gains by operating directly inside user workflows. ChatGPT Atlas pushes this model further by allowing an AI agent to browse the web, click links, fill ...

Cybercriminals don't always need malware or exploits to break into systems anymore. Sometimes, they just need the right words in the right place. OpenAI is now openly acknowledging that reality. The ...

Even as OpenAI works to harden its Atlas AI browser against cyberattacks, the company admits that prompt injections, a type of attack that manipulates AI agents to follow malicious instructions often ...

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 ...

The best defense against prompt injection and other AI attacks is to do some basic engineering, test more, and not rely on AI to protect you. If you want to know what is actually happening in ...

Discover the type of damage a cyber attack can do to any business, and some of the top ways you can prevent them.