Yan-Zero/dsh-codex
C3Use your ChatGPT subscription in DeepSeek Harness through OpenAI's Codex sign-in flow
★ 50+ · Yan-Zero/dsh-codex source on GitHub · this plugin in the registry
Yan-Zero/dsh-codex is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, executes system commands, decodes base64 payloads, starts a network server.
Installable plugin — declares a dsh.bundle manifest
What it can do
| Capability | Flag | Evidence |
|---|---|---|
| patches the dsh runtime | runtime_patch | ./cordis.patch.yml |
| executes system commands | exec | ×2 in authored code, e.g. src/bin.ts:4, src/bin.ts:34 |
| decodes base64 payloads | base64_decode | ×1 in authored code, e.g. src/imagegen.ts:204 |
| starts a network server | net_server | ×2 in authored code, e.g. src/oauth-browser.ts:59, src/oauth-browser.ts:80 |
| reads credential-class env vars | token_env | PI_OAUTH_CALLBACK_HOST |
Services it injects
invariants llm locale openAICodex remote sessions slots web
Hooks it attaches
agent/created agent/disposed agent/pre-step agent/request agent/request-error loader/volatile-update tools/change
Outbound domains
api.openai.com auth.openai.com chatgpt.com
Environment variables it reads
DSH_CODEX_PROXY PI_OAUTH_CALLBACK_HOST https_proxy HTTPS_PROXY http_proxy HTTP_PROXY all_proxy ALL_PROXY no_proxy NO_PROXY
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.