inclusionAI/Avernet

C3

Distributed agent coordination platform where agents live, connect, coordinate, execute, and evolve together.

★ 500+ · inclusionAI/Avernet source on GitHub · this plugin in the registry

inclusionAI/Avernet is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, runs code at install time, can rewrite the system prompt, executes system commands.

Installable plugin — declares a dsh.bundle manifest

What it can do

CapabilityFlagEvidence
patches the dsh runtimeruntime_patch./cordis.patch.yml
runs code at install timeinstall_scriptpostinstall: max setup
can rewrite the system promptprompt_surfacesystemPrompt
executes system commandsexec×7 in authored code, e.g. apps/bcs/crates/plugins/deepseek-harness-channel-bcn/src/configure.ts:18, apps/bcs/crates/plugins/deepseek-harness-channel-bcn/src/configure.ts:18
reads credential-class env varstoken_envBCS_IGNORE_CREDENTIALS, CLAWWEB_MIST_CREDENTIAL_TTL_MS, INSIGHT_ADMIN_CONSENT_SECRET, INSIGHT_INTERNAL_WRITE_TOKEN, INSIGHT_MIST_CREDENTIAL_TTL_MS, REPAIR_ARCA_PROXYPASS_MIST_SECRET_NAME

Services it injects

agentDefaultModel agentPresets agents credentials sessionPersistence sessions systemPrompt tools

Hooks it attaches

agent/inbox/claimed agent/inbox/discarded session/event

Outbound domains

aistudio.alipay.com cn-shanghai-ant-office.oss-alipay.aliyuncs.com agentclawproxy-pre.alipay.com agentclawproxy-prod.alipay.com agentclaw-pre.alipay.com agentclaw-prod.alipay.com codefuse.antgroup-inc.cn

Environment variables it reads

BOT_DATA_DIR OPENCLAW_DATA_DIR BCN_BOT_UUID BCS_URL BOT_TYPE CLAWWEB_PUBLIC_CONFIG_ROOT CLAWEVOLVE_SINGLEBOX_CONFIG INSIGHT_INTERNAL_WRITE_TOKEN npm_lifecycle_event MONITORING_LOCAL_PORT

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.