Swiss-based 0sec Labs open-sourced 0, an AI security harness for vulnerability investigations, code review, pentesting, reverse engineering and fix generation, MarkTechPost reports. MIT or Apache-2.0, research preview.
- Bring your own LLM from 14 providers. Runs on Apple Silicon, Linux or a container. No local GPU required.
- Pipeline: plan/discover, triage, verify in a separate session, then report (HTML, PDF, SARIF, Markdown, JSON).
- Rule of thumb from their docs: reproduce before you trust a finding.
My take
Useful as a defensive control plane around your own models and authorized targets. Keep it pointed at systems you own, and treat headline CTF scores as self-reported.
Review before you install: read the release notes yourself, back up your config, and try new versions somewhere you can afford to break first.
God Bless, and Happy hacking!
