yinhong-zhou/jevdo

C3

Just Jev it. A Jev-first agent loop with reusable actions for DeepSeek Harness.

★ 10+ · yinhong-zhou/jevdo source on GitHub · this plugin in the registry

yinhong-zhou/jevdo 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, starts a network server.

Installable plugin — declares a dsh.bundle manifest

What it can do

CapabilityFlagEvidence
patches the dsh runtimeruntime_patch./cordis.patch.yml
can rewrite the system promptprompt_surfacesystemPrompt
executes system commandsexec×21 in authored code, e.g. src/cli.ts:2, src/cli.ts:2
starts a network servernet_server×6 in authored code, e.g. reports/developer-workflows-v2/source/benchmarks/developer-workflows/dev.mjs:30, reports/developer-workflows-v2/source/benchmarks/developer-workflows/dev.mjs:45
reads credential-class env varstoken_envDEEPSEEK_API_KEY, TYPESAFE_API_KEY

Tool registrations

0 confirmed registration point(s); analysis is incomplete.

Services it injects

agents invariants llm sessionProjections sessions systemPrompt tools

Hooks it attaches

agent/pre-step llm/stream session/event

Outbound domains

api.typesafe.ai api.deepseek.com

Environment variables it reads

DEEPSEEK_API_KEY DEEPSEEK_BASE_URL DEEPSEEK_MODEL TYPESAFE_API_KEY JEV_ACTION_HOME JEV_ENDPOINT TYPESAFE_MODEL JEV_FIXED_MODEL

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.