A max-severity vulnerability in the latest Python FastAPI version of the ChromaDB project allows unauthenticated attackers to ...

New research exposes how prompt injection in AI agent frameworks can lead to remote code execution. Learn how these ...

Hugging Face hosts 352,000 unsafe model issues. ClawHub's registry contains 341 malicious AI agent skills. The AI supply chain is now the most attractive target in software security.

Critical out-of-bounds read in Ollama before 0.17.1 leaks process memory including API keys from over 300000 servers via ...

Four research teams found the same confused deputy failure in Claude across three surfaces in 48 hours. This audit matrix ...

CVE-2026-22679 exploited via debug endpoint in Weaver E-cology before 20260312, enabling RCE and system compromise.

The website for the popular JDownloader download manager was compromised earlier this week to distribute malicious Windows ...

OX Security confirmed arbitrary command execution on six live platforms and estimates 200,000 MCP servers are exposed. Here's how to audit your deployments.

As Europe pushes for sovereign AI infrastructure, Giskard is securing enterprise AI agents against manipulation, unsafe ...

Milestone Mojo release reveals a systems programming language with precise control over memory, strong types, GPU programming ...

Malicious repositories can trigger code execution in Claude Code, Cursor CLI, Gemini CLI, and CoPilot CLI with minimal or no ...

A Florida man is scheduled for execution next month after his conviction in the killing of his cousin's girlfriend and her 4-year-old daughter under a death warrant signed by Gov. Ron DeSantis ...