bloodtmai-cmyk/dsh-ai-hub
C3面向企业内部 Harness 工作台的轻量控制面
★ 5+ · bloodtmai-cmyk/dsh-ai-hub source on GitHub · this plugin in the registry
bloodtmai-cmyk/dsh-ai-hub is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It can rewrite the system prompt, executes system commands, starts a network server, reads credential-class env vars.
A skill, not an installable plugin — ships SKILL.md with no plugin manifest
What it can do
| Capability | Flag | Evidence |
|---|---|---|
| can rewrite the system prompt | prompt_surface | systemPrompt |
| executes system commands | exec | ×3 in authored code, e.g. artifacts/agent-reach/index.mjs:2, artifacts/wecom-office/runner.mjs:1 |
| starts a network server | net_server | ×1 in authored code, e.g. extension-host/src/http-server.ts:20 |
| reads credential-class env vars | token_env | AI_HUB_EXTENSION_HOST_API_KEY, LITELLM_API_KEY, MODEL_GATEWAY_API_KEY |
Services it injects
hubPluginRegistry skills systemPrompt tools
Outbound domains
mcp.exa.ai r.jina.ai gateway.example.com
Environment variables it reads
MODEL_GATEWAY_BASE_URL LITELLM_BASE_URL MODEL_GATEWAY_API_KEY LITELLM_API_KEY MODEL_GATEWAY_DEFAULT_MODEL LITELLM_DEFAULT_MODEL AI_HUB_WORKBUDDY_IDENTITY_PROVIDER_URL AI_HUB_JWT_ISSUER AI_HUB_EXTENSION_HOST_BIND_ADDRESS AI_HUB_EXTENSION_HOST_API_KEY
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.