A default low-privilege account on a LiteLLM proxy can climb to full admin and run code on the server by chaining three vulnerabilities, researchers at Obsidian Security disclosed LiteLLM is a widely ...
University of Toronto researchers have built and tested a proof-of-concept AI-driven computer worm that uses a locally hosted open-weight large language model to reason its way through a network, ...
OpenAI is moving away from models that require heavy hand-holding and toward systems that can better infer the user’s goal, ...
OpenAI has unveiled GPT-5.6 Sol, Terra, and Luna, but access remains restricted to government-approved partners ahead of a ...
OpenAI expanded its Daybreak security program on June 22, 2026, and it's easy to read the announcement as one more model drop ...
Every prompt your team sends to a language model is a potential data-exfiltration event. According to Cyberhaven's 2026 AI ...
AI-Native: Multi-model support (Gemini, OpenAI, or Local LLMs) for NL2SQL. DevOps Ready: Optimized for Kubernetes orchestration and Docker environments. Enterprise Grade: Built-in RBAC, SSO (OIDC), ...
Explore the latest news and expert commentary on Application Security, brought to you by the editors of Dark Reading ...
The key distinction from a pipeline: in a pipeline, the developer hardcodes the sequence of LLM calls. In an agent, the model decides what to do next. OpenAI's definition: "An agent is a system that ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results