Mantis Hits GitHub: 31 Composable Security Skills Form an Agent Vulnerability-Review Pipeline

Saboo_Shubham_ · x · 2026-09-10

The Mantis GitHub repo (1.1k stars) reveals a 31-skill modular architecture — plan, threat-model, reproduce, patch, report, critic, meta-agent, dedupe and more — composing a portable security-review harness for AI coding agents. The authors note it is not an official Google product; it ships with AGENTS.md and a schema for agent integration.

Related event: Google Engineers Open-Source Mantis AI Security Toolkit(2 posts)→

Original post →

More from coding & agent

coding & agent channel →