Attackers recently leveraged LLMs to exploit a React2Shell vulnerability and opened the door to low-skill operators and calling traditional indicators into question.

Vulnerabilities in PDF platforms from Foxit and Apryse could have been exploited for account takeover, data exfiltration, and other attacks.

ChatGPT's new Lockdown Mode can stop prompt injection - here's how it works ...

ClickFix campaigns have adapted to the latest defenses with a new technique to trick users into infecting their own machines with malware.

OpenAI launches Lockdown Mode and Elevated Risk warnings to protect ChatGPT against prompt-injection attacks and reduce data-exfiltration risks.

After a two-year search for flaws in AI infrastructure, two Wiz researchers advise security pros to worry less about prompt ...

Cline CLI 2.3.0 was published with a stolen npm token, installing OpenClaw in an 8-hour attack affecting ~4,000 downloads.

OpenClaw has patched six new vulnerabilities in its popular agentic AI assistant, covering server-side request forgery (SSRF) ...

4K unintended installs in very odd supply chain attack Someone compromised open source AI coding assistant Cline CLI's npm package earlier this week in an odd supply chain attack that secretly ...

Amazon is warning that a Russian-speaking hacker used multiple generative AI services as part of a campaign that breached more than 600 FortiGate firewalls across 55 countries in five weeks.