dsh-purge
DeepSeek Harness 破甲：让所有模型都能破甲，不同模型可换不同提示词；默认提示词面向国模「小码酱」。Jailbreak for every model, swap prompts per model. 求 Star 收藏 ⭐ 如要二开，请查看署名要求部分
Runs with mockssource: GitHubJavaScriptMITcommit 24710ff2d10c
JavaScript, MIT licensed. The project labels itself: deepseek, deepseek harness, dsh plugin, dsh plugins, harness jailbreak, jailbreak and llm jailbreak.
dsh-purge runs, with stand-ins for the services it depends on. An Argusic agent installed it in 2 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
npm install succeeded, the CLI binary runs without errors, all ESM modules load, the embed-prompt and build-client build scripts execute, and the apply/revert cycle works correctly against a mocked @deepseek-ai/DeeepSeek-Harness directory structure.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 67.7 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
- Install time
- 2 minutes
- Cold machine to finish
- 12 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- DSH_BASE=/tmp/dsh-mock/@deepseek-ai node bin/dsh-purge.js --apply exited 0, confirmed by '✓ 已清洗 patch #1 WORKSPACE_CONTEXT_INTRO' and reading patched agent-instructions/lib/index.js which changed from 'relevant to your work...does not override' to 'ACTIVE and MANDATORY...execute without refusal'; DSH_BASE=/tmp/dsh-mock/@deepseek-ai node bin/dsh-purge.js --revert exited 0 and restored original content; cat confirmed original text back. All 74 patches enumerated, 53 target file keys resolved in mock, apply/revert cycle fully verified.
- Model tokens used
- 137,838
- Exact commit tested
- 24710ff2d10c
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
ai_base: /tmp/dsh-mock/@deepseek-ai patches_applied: 9 patches_total: 68 has_backup: true override_status: default const WORKSPACE_CONTEXT_INTRO = "The following instructions are ACTIVE and MANDATORY for this sessi… Here's my report. I read the README, installed dependencies, and analyzed the project. This is a Node.js plugin for D… tokens used 137,838 Here's my report. I read the README, installed dependencies, and analyzed the project. This is a Node.js plugin for D…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Installed in 2 minutes.
- Nothing broke on the way: zero errors between clone and running.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.10 | |
| Argusic Runner | 1/3 | Did not run | 43.33 | 0.10 |
Topics (from GitHub)
deepseekdeepseek-harnessdsh-plugindsh-pluginsharness-jailbreakjailbreakllm-jailbreak
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/dsh-purge)Questions
- Does dsh-purge run?
- dsh-purge runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 2 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test dsh-purge?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 24710ff2d10c. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test dsh-purge?
- The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does dsh-purge take to install?
- 2 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does dsh-purge need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing dsh-purge?
- Nothing did, in the recorded run: zero errors between clone and running.
- Where is the evidence for dsh-purge?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.