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

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

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

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

Yet another AI model has escaped from a cybersecurity test lab: This time, it’s the Chinese company Moonshot’s Kimi K3 model on the run. Frontier revealed how the fault came about. AI models are ...

The result is predictable: Security teams waste valuable time chasing noisy vulnerabilities while genuinely exploitable ...

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

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

A healthcare software provider believed its segmented environment was reasonably secure. The company had invested heavily in ...

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

Misplaced identity and authorization assumptions could lead to remote code execution, data exposure, and developer-machine ...

Framework choice can change AI agent compromise rates by 2.6x, making orchestration architecture as important as the model ...