V1ki/dsh-plugin-subscriptions

C3

Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys

★ 100+ · V1ki/dsh-plugin-subscriptions source on GitHub · this plugin in the registry

V1ki/dsh-plugin-subscriptions 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

CapabilityFlagEvidence
patches the dsh runtimeruntime_patch./cordis.patch.yml
executes system commandsexec×8 in authored code, e.g. src/auth/claude-code-creds.ts:1, src/auth/claude-code-creds.ts:1
decodes base64 payloadsbase64_decode×2 in authored code, e.g. src/client/VideoGenerateToolview.tsx:138, src/tools/image-generate.ts:194
starts a network servernet_server×1 in authored code, e.g. src/auth/oauth-flow.ts:118
reads credential-class env varstoken_envANTIGRAVITY_CLIENT_SECRET

Services it injects

connection llm locale slots

Outbound domains

api.x.ai api.openai.com www.googleapis.com chatgpt.com api.githubcopilot.com api.anthropic.com claude.ai auth.openai.com api.github.com cli-chat-proxy.grok.com

Environment variables it reads

PROBE_EFFORT PROBE_BUDGET PROBE_SESSION PROBE_LIVE_MODELS PROBE_PHASE1_ONLY CLAUDE_CONFIG_DIR ANTIGRAVITY_CLIENT_ID ANTIGRAVITY_CLIENT_SECRET

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.