Anthropic published the prompt injection failure rates that enterprise security teams have been asking every vendor for

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

Hackers can use prompt injection attacks to hijack your AI chats — here's how to avoid this serious security flaw

While more and more people are using AI for a variety of purposes, threat actors have already found security flaws that can turn your helpful assistant into their partner in crime without you even ...
GIGAZINE

The AI browser 'ChatGPT Atlas' strengthens security by using automatic hacking AI that creates harmful attacks such as 'sending resignation emails without permission'

ChatGPT Atlas,' released by OpenAI in October 2025, incorporates an AI agent that can perform tasks such as information gathering and email processing. To strengthen the security of ChatGPT Atlas, ...
Dark Reading

LLMs Open to Manipulation Using Doctored Images, Audio

Attackers could soon begin using malicious instructions hidden in strategically placed images and audio clips online to manipulate responses to user prompts from large language models (LLMs) behind AI ...
CSOonline

Researchers warn of mass ‘meshing injection’ attack

Wayne Huang and the research team at Armorize have discovered a mass SQL injection coupled with a drive-by download, which they describe as a “mass meshing injection” attack. In a phone call this ...