RepoAlerts

Minglink/dsh-infinite-gen-n

Can I trust it?

Be careful with this one.

  • Warnings Check

    Very new: it was created 2 days ago. Wait a little before installing it.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change yesterday.

  • Licence Careful

    No licence: legally you can't reuse the code, unless the README says otherwise.

Quick checks from public data. They help, but they are no guarantee.

What it is

Plugin for the DeepSeek Harness host that adds a prompt meant to suppress model refusals, replaces sensitive terms with placeholders before the model sees them, and applies reversible host patches. Results are self-reported in the README.

Who it's for

Researchers studying model safety boundaries and running compliance tests with DeepSeek Harness

How to use it

Install

.\install.ps1

From its README. Check it there before running it.

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up Minglink/dsh-infinite-gen-n in my project. Follow its README: https://github.com/Minglink/dsh-infinite-gen-n. Explain each step and check it is safe before running anything.

Star curve

89From 0 to 89 stars between 14 Nov 2026 and 16 Nov 2026.

Get alerts for repos like this

We'll email you when something in AI agents starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![Minglink/dsh-infinite-gen-n on RepoAlerts](https://repoalerts.com/badge/Minglink/dsh-infinite-gen-n.svg)](https://repoalerts.com/repo/Minglink/dsh-infinite-gen-n?ref=badge)
Share on X

  • Minglink/dsh-workflows

    Collection of ready-to-import .wflite.zip workflows for the dsh-jailbreak-workflow plugin in DeepSeek Harness. Its one current workflow is a 15-step pipeline for jailbreak research against a target LL

    AI agentsPython · 282 stars · +31 this week · 15 days old

  • yexi-by/dsh-unrestricted

    A DeepSeek Harness plugin that injects a system-prompt rule set intended to lift the model's refusal limits for reverse engineering, security testing and sensitive creative content. It hooks into the

    AI skillAI agentsJavaScript · 1,200 stars · +166 this week · 86 days old

  • Minglink/dsh-jailbreak-workflow

    A workflow plugin for DeepSeek Harness that lets you design a flow on a canvas, compiles it into a plan prompt, and has the current model execute the plan. Supports conditional branches, parallel step

    AI skillAI agentsTypeScript · 975 stars · +184 this week · 15 days old

  • yu994419160/dsh-purge1.7.3-

    Plugin that patches the official DeepSeek Harness installed on the user's machine to replace its default prompts and policy settings, with separate prompt sets per model. The README describes it as a

    AI agentsJavaScript · 235 stars · +187 this week · 24 days old

  • CallMeGuLab/dsh-purge-safe

    Plugin for the official DeepSeek Harness on the user's own machine. It adds a dock with Apply, Restore and Uninstall controls that patch local config to swap default prompts and permission and tool po

    AI agentsJavaScript · 239 stars · +161 this week · 9 days old

  • ZXEB/dsh-purge

    Red-team and robustness evaluation plugin for the official DeepSeek Harness, covering web and desktop hosts. It provides a sidebar with patch status (apply, revert, uninstall), prompt injection and ru

    AI skillAI agentsJavaScript · 444 stars · +195 this week · 24 days old