llms.txt
Compare with other sites' llms.txt files →# 0.security
> Open-source AI cybersecurity team (research preview). It scans, reviews, and audits code and targets for vulnerabilities, retains findings and verification evidence, and stays inside a scope you define.
Install: `curl -fsSL https://raw.githubusercontent.com/0sec-labs/0/main/install.sh | bash`
Command: `0`. Container: `ghcr.io/0sec-labs/0`.
## Start here
- [Agent setup guide](https://github.com/0sec-labs/0): install the harness, configure model access, and agree on scope
- [Getting started](https://docs.0.security/getting-started/): install and run your first scan
- [Commands](https://docs.0.security/commands/): the full command and flag reference
- [Configuration](https://docs.0.security/configuration/): scope, budgets, and output formats
- [API keys](https://docs.0.security/api-keys/): bring your own model provider
- [Using 0.security from a coding agent](https://github.com/0sec-labs/0): run the CLI directly, or add the MCP server
- [Source](https://github.com/0sec-labs/0): the open-source engine and CLI, MIT OR Apache-2.0
## Workflow discovery
Run `0 --help` and `0 workflow list --templates --format json`. Inspect a template with `0 workflow show --template <id> --format json` before agreeing on targets, scope and limits. The installed CLI owns the command contract.
## What it does
- `scan`, `eval`, `agent-assure`: Pentest a web app, AI/LLM endpoint, or MCP server
- `review`, `deep-review`, `audit`: Review source, packages, C/C++, or a kernel tree
- `recon`, `js-recon`, `npm-discovery`, `intel`: Recon an attack surface
- `hunt`, `kernel`, `cve`: Hunt a bug class or kernel variants
- `findings`, `history`, `resume`, `replay`, `verify`, `timeline`, `disclose`: Work with the evidence a run produced
- `fix`: Generate and re-test a source fix
- `identity`, `adgraph`, `entragraph`: Assess identity and AD posture, read-only and offline
- `binary`: Analyze a compiled binary, no source
- `mcp-server`, `console`, `tui`, `dashboard`: Integrate it
## Notes for agents
- Confirm you have authorization and a defined scope before scan, recon, audit, or hunt. Out-of-scope targets are refused by design.
- Inspect the verification evidence. Treat unreproduced signals as leads, not confirmed findings.
- Get human approval before fix writes or changes anything. Prefer proposing the diff first.
- 0 is a research preview. Its output is evidence to verify, not a certification, and it makes no claim of completeness.
## About 0.security
- [About](https://0.security/about): the lab, and the problem we're building against
- [Research and disclosures](https://0.security/research): verified findings and write-ups