openma-ai/open-managed-agents

C2

Open-source Claude Managed Agents API implementation and self-hosted Claude Tag-style agent runtime. Drop-in compatible; runs on Cloudflare Workers/Durable Objects or Node.js. Apache 2.0.

★ 100+ · openma-ai/open-managed-agents source on GitHub · this plugin in the registry

openma-ai/open-managed-agents 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.

What it can do

CapabilityFlagEvidence
executes system commandsexec×37 src, e.g. packages/acp-runtime/src/registry.ts:38, packages/acp-runtime/src/registry.ts:38
decodes base64 payloadsbase64_decode×7 src, e.g. packages/cli/src/index.ts:513, apps/agent/src/runtime/session-do.ts:2557
starts a network servernet_server×4 src, e.g. packages/cli/src/index.ts:476, packages/cli/src/index.ts:2147
reads credential-class env varstoken_envANTHROPIC_API_KEY, AUTH_COOKIE_DOMAIN, AUTH_DATABASE_PATH, AUTH_DISABLED, AUTH_REQUIRE_EMAIL_VERIFY, BETTER_AUTH_SECRET

Outbound domains

openma.dev mcp.slack.com open.feishu.cn platform.claude.com api.slack.com app.openma.dev schema.org api.github.com mcp.notion.com api.githubcopilot.com

Environment variables it reads

AUTH_REQUIRE_EMAIL_VERIFY DATABASE_URL PUBLIC_BASE_URL GOOGLE_CLIENT_ID GOOGLE_CLIENT_SECRET AUTH_COOKIE_DOMAIN FILES_S3_ENDPOINT FILES_S3_BUCKET OMA_TENANT_ID OMA_BASE_URL

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.