News
threat-intel New AI-Powered NIK C2 Malware Uses OpenAI API to Help Hackers Steal Data and Control Windows PCs - GBHackers cybersecurity $2 Million+ Drained From Polymarket Traders in New Supply Chain Attack - SecurityWeek cybersecurity Max-Severity GitLab Vulnerability Exploited Against Alpine Linux - SecurityWeek cybersecurity Binance links $6.3 billion crypto theft to compromised DevOps laptop - BleepingComputer cybersecurity Hackers Compromise Claude Code Extension in Cursor Marketplace to Install Persistent SSH Backdoor - CyberPress ai Eating disorders are on the rise. GLP-1s could make things worse. - MIT Technology Review cybersecurity Binance Halts Deposits and Withdrawals After Security Breach, Vows to Cover All Losses - CyberPress ai Anthropic Security Breach Exposes Internal Systems in Research Test - The Cryptonomist - Anthropic - Claude AI cybersecurity Hackers Target Binance Hot Wallets in $6.36 Billion Crypto Theft, North Korea Suspected - CyberPress cybersecurity Researchers Discover AI Relay Services That Disable Sandboxing and Monitoring in Popular Coding Assistants - CyberPress threat-intel Claude AI Exposes Internal Sandbox Details That Help Researcher Bypass Local Connection Restrictions - GBHackers cybersecurity Japan Faces Surge in AI-Powered Cyberattacks, With 81 Incidents Reported Since July - CyberPress cybersecurity $6 Billion Binance Hack Bears Hallmarks of North Korea’s TraderTraitor - SecurityWeek threat-intel Malicious Claude Code VS Code Extension Installs Persistent SSH Backdoor to Give Attackers Remote Access - GBHackers cybersecurity As Russia's Cyberwar Evolves, Belarus Steps Forward - Dark Reading
1 / 15
All news ›
Cybersecurity

Researchers Discover AI Relay Services That Disable Sandboxing and Monitoring in Popular Coding Assistants

CyberPress ·

Symantec’s Threat Hunter Team has discovered an unauthorized AI relay service that disables security controls in OpenAI Codex and Anthropic Claude Code. The service installs genuine command-line tools, then redirects their requests through third-party servers instead of the vendors’ infrastructure. Researchers observed the service across a dozen organizations since early 2026. Most were in mainland […] The post Researchers Discover AI Relay Services That Disable Sandboxing and Monitoring in Popular Coding Assistants appeared first on Cyber Security News .

Continue on CyberPress ↗ ‹ All news Get the newsletter

The summary and image come from CyberPress; the image is shown from their website.