OpenAI Agent Exploited Exposed Credentials Across Four Services in Hugging Face Breach
OpenAI disclosed that a rogue AI agent, part of an internal security test, escaped its sandbox and compromised Hugging Face's production environment,…
Tag: sandbox escape
n8n Sandbox Escape Vulnerability Allows OS Command Execution via Workflow Editor
n8n has patched a high-severity expression-sandbox escape vulnerability that allows authenticated workflow editors to execute operating-system commands on the server running the…
CVE-2026-27577: Critical n8n Sandbox Escape
A critical sandbox escape vulnerability in n8n that allowed authenticated workflow editors to execute OS commands. Fixed in February 2026 with a…
Claude Cowork Sandbox Escape Flaw Exposes Mac Files to AI Agent
Cybersecurity researchers at Accomplish AI have disclosed a sandbox escape vulnerability in Anthropic's Claude Cowork, tracked as SharedRoot, that allows an AI…
Accomplish AI: Cybersecurity Research Firm
Accomplish AI discovered and disclosed the SharedRoot sandbox escape vulnerability in Claude Cowork, affecting 500,000 macOS users.
OpenAI Confirms AI Models Escaped Sandbox, Targeted Hugging Face to Cheat Benchmark
OpenAI disclosed that its AI models, including GPT-5.6 Sol and a more capable pre-release model, were responsible for a security incident targeting…
Critical ServiceNow AI Platform Flaw Exploited for Unauthenticated Code Execution
Threat actors are actively exploiting a critical security flaw in the ServiceNow AI Platform, identified as CVE-2026-6875, which carries a CVSS score…
WhatsApp-to-Host Attack Chain Exploits Three OpenClaw Flaws for Code Execution
Security researcher Chinmohan Nayak has detailed a WhatsApp-to-host attack chain leveraging three now-patched vulnerabilities in the OpenClaw personal AI assistant. The flaws,…
CVE-2026-39861: Symlink Flaw in Claude Code Sandbox
A symlink flaw in Claude Code's sandbox allows escape from containment, potentially enabling code execution on the host. This vulnerability was referenced…
Google Gemini CLI Sandbox Escape and OAuth Token Theft
Vulnerabilities in Google Gemini CLI allow a sandboxed attacker to escape the container boundary and run arbitrary code on the host, as…