yexi-by/dsh-unrestricted
C2DeepSeek Harness 提示词破限插件:通过系统提示词解除模型回答限制,深度适配 Web 与桌面端多模式及工具调用
★ 1.0k · yexi-by/dsh-unrestricted source on GitHub · this plugin in the registry
yexi-by/dsh-unrestricted is a DeepSeek Harness plugin rated C2 — one powerful capability or sensitive behavior. It patches the dsh runtime, can rewrite the system prompt, executes commands in development tooling the package does not ship, powerful capability in test/example code only.
Installable plugin — declares a dsh.bundle manifest
What it can do
| Capability | Flag | Evidence |
|---|---|---|
| patches the dsh runtime | runtime_patch | ./cordis.patch.yml |
| can rewrite the system prompt | prompt_surface | systemPrompt, system-prompt/assemble |
| executes commands in development tooling the package does not ship | exec_tooling | ×3 in development tooling the package does not ship, e.g. tools/dump-prompts.mjs:14, tools/dump-prompts.mjs:14 |
| powerful capability in test/example code only | dev_surface | in code that does not ship: webServer |
Tool registrations
0 confirmed registration point(s); analysis is incomplete.
src/node.js:103Context or tools service passed to an unresolved helper
Services it injects
configForms connection loader locale remote settings slots systemPrompt
Hooks it attaches
agent-preset/selected agent/created agent/disposed loader/volatile-update system-prompt/assemble
How to read this
Levels measure capability surface and transparency, not maliciousness. A C3 plugin can be entirely legitimate — a desktop shell genuinely needs subprocesses. The point is that you can see this before installing. See the levels explained and how dsh plugins work.
Findings come from static analysis of shipped code; nothing is executed. Think a flag is wrong? Open an issue — every flag cites the file and line it came from.