BotHarness/DeepSeekBot

C2

Open-source GrokBot alternative built on DeepSeek Harness. Build your personal bot team: multiple personal agents with persistent memory, identities and permissions, extensible through DSH plugins.|基于

★ 500+ · BotHarness/DeepSeekBot source on GitHub · this plugin in the registry

BotHarness/DeepSeekBot 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.

Installable plugin — declares a dsh.bundle manifest

What it can do

CapabilityFlagEvidence
executes system commandsexec×62 in authored code, e.g. apps/mobile/app.config.js:1, apps/mobile/app.config.js:1
decodes base64 payloadsbase64_decode×9 in authored code, e.g. .agents/skills/answer-me-with-html/scripts/am.mjs:11723, .agents/skills/answer-me-with-html/scripts/am.mjs:11759
starts a network servernet_server×4 in authored code, e.g. apps/mobile/scripts/stream-replay.mjs:59, apps/mobile/scripts/tob-authkit-browser.mjs:43
reads credential-class env varstoken_envEXPO_PUBLIC_MOBILE_POSTHOG_TOKEN

Tool registrations

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

3522 source file(s) omitted by size/count/encoding limits; tool count is incomplete

Outbound domains

api.workos.com market.botharness.ai schemas.android.com openfontlicense.org answer-me-with-html.com api.elevenlabs.io tailscale.com mise.jdx.dev connect.botharness.ai my-mac.tailnet.ts.net

Environment variables it reads

EXPO_PUBLIC_BUILD_COMMIT EXPO_PUBLIC_BUILD_BRANCH EXPO_PUBLIC_BUILD_TIME GOOGLE_SERVICES_JSON DEEPSEEKBOT_APP_VARIANT BOTHARNESS_BUILD_SHA EAS_BUILD_GIT_COMMIT_HASH BOTHARNESS_BUILD_TIME BOTHARNESS_MOBILE_WEB_PREVIEW XDG_CACHE_HOME

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.