Jesse-njx/dsh-cowork
C3READ + WRITE for office documents & notebooks in DeepSeek Harness — doc_read/doc_write tools (xlsx, pdf, docx, pptx, ipynb) plus MCP server and CLI
★ 1+ · Jesse-njx/dsh-cowork source on GitHub · this plugin in the registry
Jesse-njx/dsh-cowork 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, decodes base64 payloads.
What it can do
| Capability | Flag | Evidence |
|---|---|---|
| patches the dsh runtime | runtime_patch | ./cordis.patch.yml |
| can rewrite the system prompt | prompt_surface | approval, systemPrompt |
| executes system commands | exec | ×6 src, e.g. scripts/publish.mjs:14, scripts/publish.mjs:14 |
| decodes base64 payloads | base64_decode | ×1 src, e.g. packages/chatnode-wechat/src/gateway/media.ts:81 |
Services it injects
agents approval credentials fs sessions systemPrompt tools wechat
Hooks it attaches
approval/request session/event wechat/error wechat/fatal wechat/message wechat/status
Outbound domains
schemas.openxmlformats.org ilinkai.weixin.qq.com novac2c.cdn.weixin.qq.com
Environment variables it reads
WEIXIN_BASE_URL WEIXIN_ALLOW_FROM
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.