Ephemeral-AI-Lab/dsh-plugins
C3Make Deepseek Harness Great
★ 50+ · Ephemeral-AI-Lab/dsh-plugins source on GitHub · this plugin in the registry
Ephemeral-AI-Lab/dsh-plugins is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, can rewrite the system prompt, executes system commands.
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 |
| executes system commands | exec | ×9 in authored code, e.g. scripts/verify-packages.mjs:23, scripts/verify-packages.mjs:23 |
Services it injects
agentDefaultModel agents commands connection credentials jobs layout llm locale remote sessionLogDownload sessionPersistence sessionProjections sessionQuery sessions slots systemPrompt tools workbench workspaceRegistry
Hooks it attaches
agent/created agent/disposed agent/session-start agent/status approval/request session/event tools/execute tools/result user-questions/request
Outbound domains
auth.x.ai api.npmjs.org
Environment variables it reads
ComSpec Path
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.