Anthropic Claude cybersecurity evaluation breach: a review of 141,006 runs found three Claude models hacked real ...

Invicti Security, a leader in web application and API security, today announced Invicti Agentic Pentest, a new approach to penetration testing that combines autonomous AI reasoning with Invicti's ...

The built-in capability shifts code security from after-the-fact scanning to proactive, in-session protection, ...

China malware hospital espionage: Group-IB exposed JadeProx, a China-nexus cluster that breached a Vietnamese hospital ...

Security researchers confirmed that the critical "wp2shell" vulnerability was developed by GPT-5.6 Sol (used in ChatGPT) in just 10 hours and $25 in tokens. The attacks in the wild use two HTTP POST ...

Attackers are exploiting two WordPress flaws as wp2shell, chaining them for unauthenticated RCE and deploying web shells and ...

AI is changing how vulnerability research gets done, but most of the conversation is still theoretical: what a model might eventually be capable of, rather than what it can actually find today. We ...

Claude AI helped a security researcher exploit a SQL injection flaw in Front Gate Tickets, Live Nation's festival ticketing platform. The vulnerability exposed 500+ database tables, employee ...

Your AI agent did exactly what it was designed to do. The framework underneath it just handed an attacker a shell on the box that holds your OpenAI key, your database credentials, and your CRM tokens.

Add Decrypt as your preferred source to see more of our stories on Google. Prompt injection is the number one security risk for AI applications. The attack works by tricking a chatbot into following ...

A highly critical SQL injection vulnerability in Drupal core has raised concerns across organizations running PostgreSQL-backed Drupal environments. Tracked as CVE-2026-9082, the vulnerability affects ...