Technology ❯ Artificial Intelligence ❯ AI Security

Vulnerabilities

Testing Zero-Click Attacks Microsoft Copilot Bypassing Restrictions Browser Agents Prompt Injection Privacy Risks Development Tools

OpenAI to Acquire Promptfoo to Build Automated Security Into Frontier Agents

OpenAI will maintain Promptfoo’s open-source project to support enterprise testing for risks and compliance.

Microsoft Fixes 'Reprompt' Flaw That Enabled One-Click Data Theft From Copilot Personal

Anthropic Adds Native File Creation to Claude in Preview Rollout

Microsoft Fixes Zero-Click EchoLeak Flaw in Copilot as Researchers Call for AI Agent Redesign