lilyblessing/dsh-mcp-skill-panel
C3MCP 与技能管理面板：设置页展示 MCP 服务器与 Skill 目录，随时启停释放上下文占用。
★ 5+ · lilyblessing/dsh-mcp-skill-panel source on GitHub · this plugin in the registry
lilyblessing/dsh-mcp-skill-panel is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, can rewrite the system prompt, executes commands in development tooling the package does not ship, uses eval / new Function.
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 commands in development tooling the package does not ship | exec_tooling | ×12 in development tooling the package does not ship, e.g. scripts/build.mjs:5, scripts/build.mjs:5 |
| uses eval / new Function | eval | ×1 in authored code, e.g. src/preset-mcp.ts:165 |
| reads credential-class env vars in development tooling the package does not ship | token_env_tooling | in development tooling the package does not ship: MIMO_API_KEY, XIAOMI_API_KEY |
Services it injects
agentPresets agents fs loader locale skills slots systemPrompt timer tools
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.