ResearchTechnology, Cloud & SaaSCriticalDeepSeek Harness Vulnerability Allowed AI Coding Agents to Disable Their SandboxOX Security and VulnCheck disclosed CVE-2026-82533 in DeepSeek Harness, where prompt injection allowed sandboxed AI coding agents to disable their own security isolation.Mei-Lin Chen·9 Sep 2026, 14:00 IST·5 min read