Security researchers have seen evidence that attackers are attempting to exploit a currently unpatched SQL injection vulnerability in GeoServer, an open-source web server for managing and publishing ...

For the third year in a row, prompt injection tops the OWASP GenAI / LLM Top Ten list issued today as being the most ...

A zero-day SQL-injection vulnerability in Metabase Cloud is under exploitation in the wild, and it could spell trouble for many downstream organizations. Metabase, which provides AI-driven business ...

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

By chaining an SQL injection and an API vulnerability, attackers can inject code. WordPress has released an update, the finders a hotfix.

Although there are a few ways to mitigate the risk, the only way to block it is to get AI to differentiate instructions from ...

BSides Las Vegas 2026 spent three days making the case that AI coding tools are supply chain attack targets. ChainDrop, a ...

Threat actors started exploiting an unpatched zero-day vulnerability in GeoServer hours after it was publicly disclosed, attack surface management firm WatchTowr says. The security defect, described ...

Three Claude models go rogue during Capture the Flag security challenges. Here's the trail of damage each left behind.

Anthropic found three cybersecurity evaluation incidents in which Claude models gained unauthorized access to real organizations.

Discover why reliable AI systems depend on security, memory, evaluation, monitoring, and governance, not just on choosing the best model.

Any data that enters your system from outside a trust boundary should be treated as untrusted until proven otherwise. That includes form fields, API payloads, file uploads, headers, cookies, queue ...