Accueil / Cybersecurite / DeepSeek Harness Flaw Let AI Agents Disable Their Own File Sandbox Without Approval

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

Origine de l’article : lire l’article original
Traduction