GitHub Repository

AI-native red-team workbench for authorized penetration testing and vulnerability research, with specialist agents, sandboxed tooling, evidence records, and replayable timelines.

375 starsPython

AI-native red-team for penetration testing and vulnerability research

Name: AI-native red-team for penetration testing and vulnerability research
Availability: InStock
Author: yv1ing

by yv1ing·Jun 9, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidBig BrainNiche Gem

Sandboxed Docker execution keeps AI agents from wrecking your host system during pentests.

Strengths

•Docker-bound sandboxes isolate all command execution and tooling from the host
•WorkProject records persist findings and attack paths outside model context for review
•Specialist agents handle reconnaissance, code audit, reverse engineering, and crypto review

Weaknesses

•AI agent security tools are a crowded category with many competitors
•Requires explicit authorization workflow that may slow rapid testing

Post Description

AI-native red-team workbench for authorized penetration testing and vulnerability research, with specialist agents, sandboxed tooling, evidence records, and replayable timelines.

Similar Projects

Security●●Solid

Z3r0 – Multi-agent red team collaboration platform

Docker-sandboxed agent orchestration for red teams joins a crowded automated pentesting space.

Niche GemShip ItBold Bet

yv1ing

2018h ago

Security●●Solid

Ziran, security testing for AI agents

Instead of testing LLMs in isolation, ZIRAN models agents as stateful, tool‑wielding actors — it flags dangerous tool chains (e.g. read_file → http_request), runs multi‑phase trust‑building attack campaigns, and surfaces attack paths in a knowledge graph. The A2A protocol support and remote HTTPS scanner with protocol auto‑detection are concrete, unusual features; the repo (docs, examples, PyPI) suggests solid follow-through, though usefulness will depend on adapter coverage for real deployments.

Big BrainNiche Gem

leoneperdigao

103mo ago

Security●●●Banger