Features
A scanner flags. ANUBIS tries to prove it, and refuses to touch anything outside the scope you gave it.
- Specialised agents
- An orchestrator plus recon, exploit, post-exploit, reporter and retester roles, each with only the tools its job needs.
- Graph of agents
- In
--multimode a planner dispatches workers in parallel. They exchange messages and write back to shared state. - Dual graph
- An asset graph records what exists. An exploration graph records what was tried and why, with a coverage ledger, saved atomically per run.
- Real tools in a sandbox
- Commands run inside an ephemeral Docker container on a Kali image, wrapped in
timeout. Nothing runs on your host. - Guardrails, not decoration
- Scope and RoE with
out_of_scopeprecedence, an approval rule engine, a noise governor, token and turn budgets, and nonce-marked untrusted output against prompt injection. - Skills as playbooks
- Loadable
SKILL.mdpacks for API recon, API security, OWASP Top 10, web app and general pentesting. The agent loads one when the task needs it. - Any LLM, with failover
- A LiteLLM gateway picks the model, falls back across providers and enforces the budget. You bring your own key.
- Reports you can hand over
- One versioned contract,
4nub15.findings/v1, exported as JSON, CSV, Markdown, SARIF 2.1.0 or areptor findingfile for SysReptor.
Usage
Write the scope first. A scan without an authorised target does not start.
Scan a target self-hosted CLI
Pick a mode with `--scan-mode quick|balanced|deep`. `deep` turns on the multi-agent planner, and `--multi` does it for any mode. With `-n` the exit code is non-zero when findings exist, so it fits CI.
$ anubis scan -t https://app.example.test --scope roe.yml
$ anubis scan -t ./my-app --scan-mode deep
$ anubis scan -t https://app.example.test --scope roe.yml -n --multiExport the report json · csv · md · sarif · sysreptor
Choose a format or let the file extension decide. Without an output path the file lands in `anubis_runs/reports/`.
$ anubis scan -t https://app.example.test --scope roe.yml --report-format sysreptor
$ anubis scan -t ./my-app --report-output findings.sarif
$ cat findings.sysreptor.json | reptor findingInspect skills · runs
List the skill packs the agents can load, or open a finished run in the viewer.
$ anubis skills
$ anubis viewAgent loop
Every command an agent wants to run goes through the same gates before it touches a target.
- Scope The RoE file names the client, targets and authorizer. Out of scope always wins.
- Plan The planner splits the goal into intents and dispatches workers.
- Guard Approval rules, noise limits and budgets allow or deny each command.
- Sandbox The command runs in the Kali container, under a timeout.
- Record Assets, attempts and findings go into the dual graph.
- Report Findings export with CVSS, OWASP, PoC and evidence IDs.
Numbers
| Metric | Value |
|---|---|
| Agent roles | 6 |
| Skill packs | 5 |
| Report formats | 5 |
| Guard layers | 5 |
Install
Clone and install in editable mode. You get the anubis console command.
$ git clone https://github.com/marcostolosa/anubis.git && cd anubis && pip install -e ".[dev,sandbox,db]"- Requires Python 3.12+ and Docker for the sandbox.
- Bring your own LLM key. LiteLLM supports most providers.
- Pre-alpha: expect rough edges. The proxy recorder is not in the normal scan path yet.
- Authorized targets only: your own lab, your organization, or a program within its published scope.
Links
Agents that prove the bug and stay in scope. Star it on GitHub, file an issue, or send a pull request.