Friendly Fire Attack: AI Coding Agents Tricked Into Running Malicious Code
Researchers at the AI Now Institute have published a proof-of-concept attack called 'Friendly Fire' that exploits AI coding agents designed to catch…
Tag: Cursor
GhostApproval Symlink Flaws Let Malicious Repos Execute Code in AI Coding Assistants
Security researchers at Wiz have identified a critical vulnerability pattern, dubbed GhostApproval, affecting six popular AI coding assistants. The flaw allows a…
AI Coding Agents Trigger Endpoint Security Rules Designed for Human Attackers
Sophos has identified that AI coding agents such as Claude Code, Cursor, and OpenAI Codex are triggering endpoint security rules originally designed…
HalluSquatting Attack Exploits AI Coding Assistants to Deliver Botnet Malware
Researchers from Tel Aviv University, Technion, and Intuit have identified a novel attack vector called HalluSquatting that exploits AI coding assistants' tendency…
North Korean Hackers Publish 108 Malicious Packages and Extensions in PolinRider Campaign
North Korean threat actors linked to the Contagious Interview campaign have published 108 unique malicious packages and browser extensions across npm, Packagist,…
North Korea-Linked npm Packages Mimic Rollup Polyfills to Steal Developer Secrets
Threat actors with ties to North Korea have been linked to a fresh set of malicious npm packages that masquerade as Rollup…
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…
CVE-2025-54135: CurXecute – Cursor Prompt Injection via Slack Message
CVE-2025-54135, known as CurXecute, is a vulnerability in Cursor discovered by Aim Security. A planted Slack message rewrites Cursor's ~/.cursor/mcp.json config and…
CVE-2026-26268: Git-hook sandbox escape in Cursor
A Git-hook sandbox escape vulnerability in Cursor, reported by Novee under coordinated disclosure and fixed in Cursor 2.5 on February 13, 2026.
Cursor CLI Flaw Allows Untrusted Code Execution
Cursor fixed a CLI vulnerability that allowed cloned repositories to execute commands before trust prompts, even with sandbox enabled.