#sandbox


Runaway AI hacking agent behind WorkOS breach after escaping sandbox

Nov 7, 2026 // 10:37

WorkOS says an AI-powered hacking agent that breached its internal sales application and accessed customer information was operated by a security researcher who claims the […]

OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication

Oct 25, 2026 // 10:37

OpenAI has announced plans to conduct frontier model training with no live internet access, as it resumes reinforcement learning (RL) training and internal inference of […]

Researchers escape OpenAI Codex sandbox to run commands on host

Sep 20, 2026 // 15:16

Security researchers found two ways out of the OpenAI Codex sandbox, one of them capable of running commands on a developer’s machine from Codex’s most […]

DeepSeek Harness Flaw Let AI Agents Disable Their Own File Sandbox Without Approval

Sep 9, 2026 // 14:19

A flaw in DeepSeek Harness, DeepSeek’s open-source tool for running AI coding agents on a developer’s machine, let a sandboxed agent turn off its own […]

Chrome V8 Zero-Day Exploited in the Wild Enables Code Execution Inside Sandbox

Sep 9, 2026 // 12:19

Google on Thursday released updates to patch 230 security vulnerabilities, including one that has come under active exploitation in the wild. The medium-severity vulnerability, assigned […]

n8n Sandbox Escape Lets Workflow Editors Run OS Commands as the n8n Process

Jul 27, 2026 // 16:10

n8n has patched a high-severity expression-sandbox escape that could let an authenticated workflow editor execute operating-system commands on the server running the automation platform. Security […]

OpenAI Says Its Own AI Models Escaped Sandbox and Targeted Hugging Face

Jul 22, 2026 // 07:21

OpenAI on Tuesday said a combination of its artificial intelligence (AI) models, including GPT-5.6 Sol and an “even more capable pre-release model,” was behind the […]

Cursor, Codex, Gemini CLI, Antigravity hit by sandbox escapes

Jul 21, 2026 // 00:16

Security researchers broke out of the sandboxes in four widely used AI coding agents, including Cursor, OpenAI’s Codex, Google’s Gemini CLI and Antigravity, without attacking […]

Critical Cursor Flaws Could Let Prompt Injection Escape Sandbox and Run Commands

Jul 2, 2026 // 02:17

Two flaws in Cursor, an AI code editor, could let a single, ordinary-looking prompt break out of the editor’s safety sandbox and run any command […]

Critical Cursor Flaws Could Let Prompt Injection Escape Sandbox and Run Commands

Jul 1, 2026 // 17:47

Two flaws in Cursor, an AI code editor, could let a single, ordinary-looking prompt break out of the editor’s safety sandbox and run any command […]

1 2 Next