ruvnet/ruflo

C2

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federa

★ 73k+ · ruvnet/ruflo source on GitHub · this plugin in the registry

ruvnet/ruflo is a DeepSeek Harness plugin rated C2 — one powerful capability or sensitive behavior. It runs code at install time, executes system commands, 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
runs code at install timeinstall_scriptpostinstall: node ./scripts/postinstall.cjs
executes system commandsexec×146 in authored code, e.g. .claude/statusline.mjs:6, .claude/statusline.mjs:6
starts a network servernet_server×2 in authored code, e.g. plugins/ruflo-ai-team/src/server.mjs:125, plugins/ruflo-chatgpt-federation/src/server.mjs:157
reads credential-class env varstoken_envBENCH_ANTHROPIC_API_KEY, BENCH_LLM_API_KEY, CGF_ACCESS_TOKEN, CGF_CALLER_TOKEN, CGF_EXPECTED_PUBKEY, CGF_OAUTH_CLIENT_ID

Outbound domains

auth.cognitum.one chatgpt.com openrouter.ai chat.openai.com claude.ai team.ruv.io chatgpt-federation-875130704813.us-central1.run.app generativelanguage.googleapis.com api.anthropic.com api.deepseek.com

Environment variables it reads

CLAUDE_PROJECT_DIR CLI_CORE CGF_CALLER_TOKEN CLAUDE_FLOW_ROUTER_PARALLEL_LOG DEBUG BUDGET_QUIET RUFLO_HOOK_SKIP_NPX RUFLO_DEBUG GITHUB_SAFE_DRY_RUN GITHUB_ACTIONS

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.