Hackers are exploiting two authentication bypass vulnerabilities in the Qinglong open-source task scheduling tool to deploy ...

In a blog post on Wednesday, Mohan Pedhapati (s1r1us), CTO of Hacktron, described how he used Opus 4.6 to create a full ...

An AI agent bypassed sandbox controls in an a16z study, discovering a way to use tools it was not explicitly granted access ...

Hackers are targeting sensitive information stored in the LiteLLM open-source large-language model (LLM) gateway by ...

Recovery efforts have stabilized Aave after the KelpDAO exploit, but governance delays and legal risks continue to cloud the ...

A critical SQL injection vulnerability in the open-source AI gateway LiteLLM, tracked as CVE-2026-42208, was exploited less than two days after being listed in the GitHub Advisory Database. Attackers ...

AI agents have become so advanced that non-experts can now use them to autonomously identify and write working code for DeFi ...

CVE-2026-42208 exploited within 36 hours of disclosure, exposing LiteLLM credentials, risking cloud account compromise.

Aave deposits dropped $16.2 billion after the KelpDAO exploit, pressuring Ethereum; $4,000 in April at 15% YES.

The April 2026 Vercel security incident continues to extend past initial claims. The incident, which was said to involve what ...

TL;DR AI risk doesn’t live in the model. It lives in the APIs behind it. Every AI interaction triggers a chain of API calls across your environment. Many of those APIs aren’t documented or tracked.

RedSun exploit targets Microsoft Defender zero-day, granting SYSTEM access on fully patched Windows systems with no patch ...