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

Notícia de segurança recolhida automaticamente.

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

Fonte original: Ler artigo completo aqui