voyager-crew/voyager

C2

Enhancement suite for Gemini, AI Studio, Claude, ChatGPT & DeepSeek — plus a prompt manager for any website, DeepSeek Harness included. / 面向 Gemini、AI Studio、Claude、ChatGPT 与 DeepSeek 的增强套件;其中的提示词管理器可

★ 20k+ · voyager-crew/voyager source on GitHub · this plugin in the registry

voyager-crew/voyager is a DeepSeek Harness plugin rated C2 — one powerful capability or sensitive behavior. It executes system commands, decodes base64 payloads, starts a network server, reads credential-class env vars.

A skill, not an installable plugin — ships SKILL.md with no plugin manifest

What it can do

CapabilityFlagEvidence
executes system commandsexec×16 in authored code, e.g. scripts/build-edge.js:7, scripts/build-edge.js:7
decodes base64 payloadsbase64_decode×4 in authored code, e.g. scripts/verify-katex-export.ts:428, scripts/verify-katex-export.ts:536
starts a network servernet_server×2 in authored code, e.g. scripts/launch-chrome.cjs:225, scripts/launch-chrome.cjs:227
reads credential-class env varstoken_envAFDIAN_TOKEN, CLIENT_SECRET, GH_TOKEN, GITHUB_TOKEN

Outbound domains

gemini.google.com claude.ai voyager.nagi.fun www.googleapis.com accounts.google.com afdian.com discord.gg oauth2.googleapis.com api.github.com business.gemini.google

Environment variables it reads

CHROME_BIN GITHUB_TOKEN CLIENT_ID CLIENT_SECRET AFDIAN_USER_ID AFDIAN_TOKEN SPONSORS_STRICT CHROME_OPEN_URL CHROME_OPEN_BUILD_TIMEOUT_MS CHROME_OPEN_POLL_INTERVAL_MS

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.