Critical Cursor Flaws Enable Zero-Click Sandbox Escape via Prompt Injection
Two critical vulnerabilities in Cursor, an AI-powered code editor, allow prompt injection attacks to escape the editor's safety sandbox and execute arbitrary…
Two critical vulnerabilities in Cursor, an AI-powered code editor, allow prompt injection attacks to escape the editor's safety sandbox and execute arbitrary…
A Git-hook sandbox escape vulnerability in Cursor, reported by Novee under coordinated disclosure and fixed in Cursor 2.5 on February 13, 2026.
A vulnerability in WebKit that could allow a malicious website to process restricted web content outside the sandbox.
A chain of three vulnerabilities in LiteLLM, a widely deployed open-source AI gateway, allows low-privilege users to escalate to full admin and…
X41 D-Sec independently found a sandbox escape path in LiteLLM's Custom Code Guardrail playground endpoint, which bypassed a regex deny-list through runtime…
Endor Labs, a cybersecurity company, identified a critical vulnerability in the isolated-vm Node.js library. The flaw, GHSA-864f-rcv7-6rh4, allows sandboxed code to escape…