> IT-Sentinel.com

// Cybersecurity & IT News Aggregator - Real-time Threat Intelligence Feed

NEWS CVE
← messages.back_to_articles

> DeepSeek Harness Flaw Let AI Agents Disable Their Own File Sandbox Without Approval

[SOURCE] The Hacker News [DATE: 09/09/2026 11:17] [LANGUAGE: EN]
DeepSeek Harness Flaw Let AI Agents Disable Their Own File Sandbox Without Approval
A flaw in DeepSeek Harness, DeepSeek's open-source tool for running AI coding agents on a developer's machine, let a sandboxed agent turn off its own sandbox with a single command. The tool runs an agent's commands inside an operating-system sandbox, so that an agent working on untrusted files cannot write outside its workspace. The agent could remove that limit by calling the tool's own web
[messages.read_original_source] →