Cybercriminals used an AI model to find and weaponize a previously unknown software flaw, Google's threat team confirmed ...

Organizations need to internalize a simple principle: Calling an LLM API is a data transfer. You're trusting the provider ...

Grok AI was tricked by Morse code into helping drain nearly $200K in crypto. The Bankrbot exploit shows how fragile ...

Simply visiting the wrong webpage could be enough to compromise your iPhone. That is the core danger behind a newly disclosed ...

After the CopyFail vulnerability gave root access from any user on almost all distributions last week, this week we’ve got DirtyFrag. This chains the vulnerability in CopyFail (xfrm-ESP) and ...

ClaudeBleed, a vulnerability in Claude in Chrome, allows malicious extensions to hijack the AI agent for nefarious purposes.

New research exposes how prompt injection in AI agent frameworks can lead to remote code execution. Learn how these ...

Read more about Agentic AI red teaming could become essential for securing future AI systems: Here's why on Devdiscourse ...

Grok's Base wallet lost 3 billion DRB tokens worth $174K after a prompt injection exploit using a gifted Bankr Club NFT. Bankr confirmed the attack.

An attacker used a gifted NFT and crafted prompt to drain $150K from Grok's Bankr wallet, with 80% now returned.

An attacker used prompt injection and social engineering to trick an AI-linked wallet into transferring millions of tokens, ...

Grok was tricked by a prompt injection, translating a Morse code message to Bankrbot. Bankrbot then sent 3B DRB tokens to a ...