834063245-creator/LantaiAgent

C3

I’m a helpful assistant

★ 10+ · 834063245-creator/LantaiAgent source on GitHub · this plugin in the registry

834063245-creator/LantaiAgent is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, runs code at install time, executes system commands, uses eval / new Function.

Installable plugin — declares a dsh.bundle manifest

What it can do

CapabilityFlagEvidence
patches the dsh runtimeruntime_patch./cordis.patch.yml
runs code at install timeinstall_scriptinstall: node scripts/install.mjs
executes system commandsexec×45 in authored code, e.g. scripts/build-builtin-plugins.mjs:42, scripts/build-builtin-plugins.mjs:42
uses eval / new Functioneval×3 in authored code, e.g. src-ui/src/agent/code-run/bootstrap.ts:265, src-ui/src/agent/dynamic-runner/sandbox.ts:97
decodes base64 payloadsbase64_decode×7 in authored code, e.g. scripts/cdp-shot.cjs:85, src-ui/src/app/chat/image-intake.ts:182
reads credential-class env varstoken_envANTHROPIC_KEY, DEEPSEEK_KEY, GLM_KEY

Services it injects

activation capabilities commands fs llm overlays panels prompts renderers rootViews sessionPersistence shell shellRows space subagents tools workspaces

Outbound domains

api.deepseek.com api.anthropic.com open.bigmodel.cn api.openai.com api.github.com gateway.example.com api.minimax.io api.moonshot.ai opencode.ai chatgpt.com

Environment variables it reads

VITEST LOOKAHEAD ANTHROPIC_MODEL DEEPSEEK_KEY GLM_KEY ANTHROPIC_KEY ANTHROPIC_BASE_URL OLLAMA_BASE_URL

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.