Permiso researchers found ChatGPhish, a prompt-injection issue that can cause ChatGPT summaries to display phishing links, ...

A team of security researchers chained two vulnerabilities in LiteLLM, the popular open-source proxy that routes enterprise traffic to large language model providers, and walked away with arbitrary ...

Hackers can hijack ChatGPT, Claude, and Gemini with nothing but a sentence. OpenAI says the problem may never be fully solved.

Unlike traditional cyberattacks that exploit software vulnerabilities, prompt injection targets an AI model's ability to ...

The latest flare-up in the debate over AI-assisted coding did not come from a new model release or a benchmark result. It came from a single ...

Cisco has released almost two dozen security updates. They close several high-risk flaws, for example in Unity Connection.

What is OpenClaw? Learn how this AI agent works, how to set it up step-by-step, and how it can help automate tasks across ...

1Password says AI coding agents should never hold persistent secrets, introducing a just-in-time credential model for OpenAI Codex designed to keep credentials out of prompts, code repositories, and ...

"Many agent frameworks allow users to install skills from online registries so the agent can discover and use new ...

Technical report identifies Gate AI as one of the top performing AI security gateways across 16 public prompt injection ...

"Prompt injection" on AI platforms is the new frontier of social engineering, writes ANNA COLLARD, SVP of content strategy and CISO advisor at KnowBe4 Africa.

Shadow AI introduces new pathways for data leakage, policy failure, and adversary access beyond the scope of traditional security.