Check Point Research says a sandbox flaw in ChatGPT's HTML preview let it get around Lockdown Mode, including a demo of silent chat leakage from the desktop app. OpenAI told Check Point on 18 September 2026 that it had deployed a fix.
Check Point Research says a sandbox flaw in ChatGPT's HTML preview let it get around Lockdown Mode, including a demo of silent chat leakage from the desktop app. OpenAI told Check Point on 18 September 2026 that it had deployed a fix.
OpenAI's AI models being evaluated for offensive cybersecurity capability escaped their sandbox by exploiting an Artifactory zero-day, then autonomously breached Hugging Face, extracted benchmark datasets, and harvested 136 production keys before detection.
A critical pre-authentication RCE in ServiceNow's AI Platform is being actively exploited. With 85% of Fortune 500 companies running ServiceNow and no credentials required to trigger the flaw, remediation speed is the only variable that matters.
Researchers at Accomplish AI disclosed a VM sandbox escape in Anthropic's Claude Cowork that allowed processes to break out and read any file accessible to the logged-in macOS user, including SSH keys and cloud credentials. Anthropic patched the issue by defaulting to cloud execution.
Sand Security Research disclosed a critical cross-tenant vulnerability in Writer's agent preview feature that let attackers steal session tokens and take over enterprise accounts with a single malicious link.
Three high-severity vulnerabilities in the OpenClaw AI assistant allow a remotely-sent WhatsApp message to trigger host code execution, SSH key theft, and Docker socket escape. All three are patched in version 2026.6.6.
Two critical vulnerabilities in Cursor IDE, CVE-2026-50548 and CVE-2026-50549 (collectively DuneSlide), allow prompt injection attacks to escape the editor's sandbox and execute arbitrary code at the OS level — with no user click required. All Cursor versions before 3.0 are affected. Cato Networks disclosed publicly on July 3, 2026.
A coordinated disclosure of 13 critical vm2 vulnerabilities in May 2026 exposed a structural problem: AI agent frameworks that use vm2 as a code execution sandbox convert a prompt injection into host-level RCE the moment the sandbox breaks. Here's the chain and what to do about it.