StyxNether/dsh-auto-approval

StyxNether★ 1JavaScript最后同步: 2026-08-14

在 GitHub 打开

Trusted Auto: a middle permission tier for DeepSeek Harness between workspace-write and danger-full-access, auto-approving harmless commands and trusted-area targets

README 摘要

dsh-auto-approval 🌐 Language : English 简体中文 A middle permission tier for DeepSeek Harness, between Workspace Write and Full access (danger-full-access): it adds a auto-approval preset to the permission settings and backs it with an automated approval answerer that approves harmless commands and operations whose target lies inside configured trusted areas — including areas outside the current workspace — and asks the user for everything else. ⚠️ Scope control, not a security boundary. This plugin automates the human approval step for a narrow, verifiable class of requests. The DSH sandbox still confines every non-escalated call; an auto-approved call runs with the wider mode for exactly that one call (the same one-shot grant a human click would produce). Do not use it on machines or sessions you would not trust a human operator to run commands on. What it does Workspace Write Auto Approval (this plugin) Full access Sandbox mode workspace-write workspace-write danger-full-access Approval policy ask ask never Writes inside workspace / temp allowed allowed allowed Harmless commands (see rule table) ask auto-approved never asks Targets inside trusted areas ask auto-approved never asks …

在 GitHub 查看完整 README →
Tools / Devdeepseek-harnessdsh-plugin

分类