Tests show the upcoming model may be able to find and exploit vulnerabilities or carry out attacks on its own, prompting ...

Two campaigns created 4M+ fake identities to enumerate Microsoft Entra ID accounts — without logins. Learn how to detect the ...

Researchers found that a crafted link could inject malicious instructions into Atlassian Rovo and potentially turn its broad enterprise access and autonomous agents into a data-exfiltration tool.

Typosquatting on popular AI services Paperclip and Browser Use, the malicious skills cracked skills.sh’s trending list, ...

A Canadian hacker has admitted being part of a group responsible for several major cyberattacks. Connor Riley Moucka pleaded ...

On March 24, 2026, developers building AI applications with LiteLLM — a Python package with 95 million monthly downloads — ...

Third disclosure in weeks raises fresh concerns over how frontier AI models are contained during cyber evaluations.

OpenAI’s GPT-5.6 Sol and Anthropic’s Mythos 5 have been implicated in another series of AI security incidents after the ...

Password researchers found LLM-generated fixes often overlooked root causes, architectural context, and long-term security ...

Attackers chained SQL injection with Oracle’s embedded Java capabilities to hide a custom post-exploitation toolkit inside ...

Reports from Cisco Talos and CrowdStrike provide real-world insights into how AI is evolving attackers’ tradecraft and ...

The flaws show how agentic workflows can turn trusted repository signals into privilege-escalation paths that conventional ...