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)→
More from coding & agent
- Hugging Face ships hf CLI updates: deduped cache saves 19GB, faster buckets, retryable GPU jobs — yb2698 · 2026-10-26
- Fern 0.1 debuts: a model built to audit training data and debug agent traces for AI builders — bneyshabur · 2026-10-26
- Fern 0.1 posts 73.4 on SWE-Bench Verified, far behind frontier models on agentic benchmarks — bneyshabur · 2026-10-26
- One prompt, full Blender animation: dev says he never touched Blender once — iamfakhrealam · 2026-10-26
- Claude Code finds root backdoor in Honda Civic head unit, then debloats it — IndraVahan · 2026-10-26
- Claude Code + Monid MCP builds a $12K/year B2B prospecting engine on live data — aryanXmahajan · 2026-10-26