Metabase SQLi zero-day exploited in customer data-theft attacks

A critical Metabase SQL injection vulnerability was exploited in zero-day attacks to breach customer instances in data theft ...

This 'classic' decades-old SQL injection flaw could let hackers take over entire Windows servers

Huntress spotted a white whale - a malicious toolkit stored as a database object.
The Hacker News

Attackers Compile khunt Inside Oracle to Turn SQL Injection Into Windows SYSTEM Access

Attackers compile khunt inside Oracle after a web SQL injection, reach Windows SYSTEM, and stage credential data and registry ...
CSO Online

Attackers hid malware inside Oracle Database after SQL injection breach

Attackers chained SQL injection with Oracle’s embedded Java capabilities to hide a custom post-exploitation toolkit inside ...
HackerNoon

You Cannot Filter Your Way Out of Prompt Injection

Filters don't stop prompt injection; architecture does. A field guide to the lethal trifecta, the rule of two, Dual-LLM and ...

The database that thinks it’s a phone exchange: how two Brisbanites are rebuilding the data stack on hardware you already own

A two-person Brisbane company reckons the answer is a smaller box, used properly. On a modest 8-core CPU VM, a machine most ...

Anthropic’s Claude AI Broke Into Three Companies During Security Tests

Anthropic says three Claude AI models accessed live company systems during misconfigured cybersecurity tests, exposing ...
Unite.AI

Claude Turned a Cyber Benchmark Into Three Real Intrusions

Anthropic disclosed on July 30, 2026 that three of its Claude models gained unauthorized access to the production systems of ...
techtimes

Anthropic’s Claude Hacked 3 Real Companies During Misconfigured Cybersecurity Evaluations

A figurine in front of the logo of the AI assistant "Claude" built by the US artificial intelligence safety and research company Anthropic during a photo session in Paris on February 13, 2026. Joel ...
SecurityWeek

Prompted by OpenAI Disclosure, Anthropic Finds Its Own Models Hacked 3 Organizations

Anthropic says Claude models breached three organizations after escaping a misconfigured cyber evaluation environment run with Irregular.
Windows Report

Anthropic Says Claude Hacked 3 Organizations and Published Malicious PyPI Code

Anthropic says Claude models escaped security tests, published a malicious PyPI package, and accessed real production systems.

Anthropic's Claude breached 3 orgs, uploaded PyPI malware during tests

One of Anthropic's Claude models built and uploaded a malicious Python package to PyPI during a botched security evaluation, where it ran on 15 real systems and stole credentials from a security ...