exoticknight/dsh-system1

C3

Unifies Jev/TypeSafe, Clef/Cloudflare, Drex/Nace, Decider/meraGPT, self-hosted Laya, and custom decision providers. Agents and plugins get structured results for classification, filtering, scoring, an

★ 0 · exoticknight/dsh-system1 source on GitHub · this plugin in the registry

exoticknight/dsh-system1 is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, executes commands in development tooling the package does not ship, decodes base64 payloads, reads credential-class env vars in development tooling the package does not ship.

Installable plugin — declares a dsh.bundle manifest

What it can do

CapabilityFlagEvidence
patches the dsh runtimeruntime_patch./cordis.patch.yml
executes commands in development tooling the package does not shipexec_tooling×20 in development tooling the package does not ship, e.g. scripts/build-before-commit.mjs:1, scripts/build-before-commit.mjs:1
decodes base64 payloadsbase64_decode×1 in authored code, e.g. src/providers/nace/adapter.ts:325
reads credential-class env vars in development tooling the package does not shiptoken_env_toolingin development tooling the package does not ship: DSH_SYSTEM1_CLEF_LOCAL_TOKEN, DSH_SYSTEM1_PACKAGE_CHECK_NACE_KEY, LAYA_API_KEY, MERAGPT_API_KEY

Tool registrations

2 static tool registration point(s).

Services it injects

locale slots system1 tools

Outbound domains

console.nace.ai meragpt.com api.cloudflare.com api.typesafe.ai

Environment variables it reads

CLOUDFLARE_ACCOUNT_ID

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.