Lanxi26/dsh-cluster
C3画布式多智能体协作插件 | Canvas-based multi-agent cooperation plugin for DeepSeek Harness
★ 1+ · Lanxi26/dsh-cluster source on GitHub · this plugin in the registry
Lanxi26/dsh-cluster 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, uses eval / new Function.
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 | ×4 src, e.g. packages/dsh-cluster-agent-fs/lib/index.js:3, packages/dsh-cluster-agent-fs/lib/index.js:327 |
| uses eval / new Function | eval | ×1 src, e.g. packages/dsh-client-ui-cluster/lib/client.js:148 |
| decodes base64 payloads | base64_decode | ×2 src, e.g. packages/dsh-client-ui-cluster/lib/client.js:1313, packages/dsh-client-ui-cluster/lib/client.js:1364 |
Services it injects
agents clusterAgentFs invariants locale remote sessions slots systemPrompt tools workspaces
Hooks it attaches
connection/reset
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.