AI Now’s Friendly Fire PoC shows Claude Code and Codex running README-planted payloads on hosts when autonomous command ...

Researchers at Zimperium have uncovered RedWing, a new Android malware-as-a-service sold through Telegram with subscription tiers, a support bot, and how-to videos. Once installed, it can steal ...

Malicious packages on the Node Package Manager (npm) and the Python Package Index (PyPI) delivered stealer malware to ...

According to Socket, malicious payment SDK packages on npm and PyPI are harvesting developer credentials and CI/CD ...

a laptop screen with a webpage of the IT Army of Ukraine group of volunteer hackers. The IT Army of Ukraine first set up in the wake of Russia's devastating attack, and has since hugely grown in ...

Rogue Agent, a vulnerability in Google Cloud Dialogflow CX, allowed attackers to control agents and exfiltrate sensitive data.

ESET Research has released its H1 2026 Threat Report with statistics from December 2025 through May 2026.ClickFix – a social engineering ...

In the brief history of AI security, the prompt injection has quickly become the top threat. Large language models are ...

The first AI agent ran a ransomware attack end to end, signaling a shift to machine-speed cyberattacks and autonomous defense ...

Sysdig says JADEPUFFER may be the first agentic ransomware case, exposing how AI agents can turn old credential failures into database destruction. JADEPUFFER is a warning about exposed AI ...

A threat group researchers call "Armored Likho" has gained access to government agencies and electrical power entities in ...

Zscaler found attackers using SEO poisoning and hidden prompts in malicious websites to manipulate AI agents into making cryptocurrency payments.