Discover how the Rogue Agent vulnerability in Google Dialogflow CX enabled persistent AI agent compromise, data exfiltration, ...

An exposed WP-SHELLSTORM server revealed tools, logs, cloud credentials, and thousands of webshells used in a large website ...

IBM and Red Hat have launched Lightwell to automate vulnerability remediation across enterprise open-source software ...

JadePuffer, a ransomware operation, used an AI agent to carry out much of the intrusion chain from reconnaissance, key theft, ...

It only took a little prompting to hijack the biggest AI models ...

Sometimes a work of art finds itself ground-zero to a memorable moment, a zeitgeist, like when Charli ...

Ethereum gossipsub vulnerability CVE-2026-34219 lets any unauthenticated peer crash a validator with a single crafted PRUNE ...

A PNG hiding a prompt injection could steal your repo's secrets, researchers demonstrate. The technique, dubbed 'Ghostcommit, ...

QR code phishing – also known as quishing – has reached record levels in ESET telemetry. ESET analyzed nearly 900,000 AI ...

In other news, a DHS database was hacked, Adobe is releasing patches twice a month, and Canada has disrupted ransomware operations.

AI agent security now has a purpose-built open-source guardrail: Ant Group released SingGuard-NSFA, a free framework that catches prompt injection and credential-theft patterns before AI agents ...