AgentsSeptember 9, 2026via MarkTechPost

Google Open-Sources Mantis: A Modular Skills Toolkit That Lets Coding Agents Find, Reproduce and Patch Vulnerabilities

Why it matters

Mantis demonstrates agent autonomy scaling into real security workflows. This is the first production-grade open toolkit for agents to execute the full vulnerability lifecycle without human intervention—a blueprint for how agents move from narrow tasks to complex, multi-step professional work.

Key signals

  • Google open-sourced Mantis under Apache 2.0
  • Stack-agnostic security skills toolkit for AI coding agents
  • Full vulnerability lifecycle automation: sweep → filter → reproduce → patch → re-attack → score
  • Sandbox-based reproduction and testing
  • Risk scoring built in
  • Released as demonstration-only (production readiness flagged)
  • Published September 9, 2026

The hook

Google open-sourced Mantis: a modular toolkit that turns coding agents into autonomous security engineers—finding, reproducing, and patching vulnerabilities end-to-end.

Google has open-sourced Mantis, a stack-agnostic toolkit of security review skills for AI coding agents. It runs the full vulnerability lifecycle: sweep the code, filter false positives, reproduce the bug in a sandbox, patch it, re-attack the patch, then score the risk. Apache 2.0, and documented as

The week's key stories, every Friday.

For practitioners and enthusiasts — free, in your inbox.

Free forever. No spam.

Google Open-Sources Mantis: A Modular Skills Toolkit That Lets Coding Agents Find, Reproduce and Patch Vulnerabilities | KeyNews.AI