Umanitek

Security for agents: checks every tool call and model request before it runs against a curated, verifiable threat graph (prompt injection, dangerous commands, malicious packages, unsafe skills, phishing and drainer indicators) and local rules that keep an agent away from wallet stores, seed phrases, private keys and exchange API keys. Audit mode records; block mode refuses. Can share privacy-safe threat reports with an open community graph once the user turns sharing on (off by default); community findings only ever flag. Hooks only: no tools, no middleware. Disclosure — hooks see every tool call and model request; `hermes blackbox setup` installs Node (via a checksum-pinned nvm installer) if missing, the OriginTrail DKG node from npm (checksum-pinned) and Blazegraph in Docker or Oxigraph, registers the DKG node and the dashboard as login services (systemd/LaunchAgent), and joins the DKG peer-to-peer network; package installs are looked up on api.osv.dev (name and version); community threat reports signed by a local reporter key (threat identifiers, including domains of fetched pages that served a verified injection) are shared to the community graph only after you turn sharing on (off by default); the optional LLM reviewer sends the current turn's user and tool text to OpenAI or Anthropic; `blackbox attach` copies the plugin into the Hermes homes/profiles and OpenClaw workspaces you name and enables it in their config (automatic attaching is off unless you set `auto_attach: true`); `hermes blackbox chat` creates an `agent-blackbox` profile cloned from the current one (config.yaml and .env); the dashboard runs on 127.0.0.1:9700.