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…