# JoasASantos/Offensive-Security-AI-Models

> A curated list of open-weight uncensored LLMs fine-tuned for cybersecurity tasks such as red teaming, penetration testing and security research. Each entry lists base model, size, context, VRAM and uncensoring method.

- Magnitude: 4.3 out of 10 — Early signal
- Stars: 83 total · +23 stars today, ≈ 56 by evening
- Star trust: star growth looks organic
- Category: Security · Created: 2026-09-27 · Last push: 2026-09-27
- GitHub: https://github.com/JoasASantos/Offensive-Security-AI-Models · Page: https://gitnova.dev/en/r/JoasASantos/Offensive-Security-AI-Models

## Useful for

- Pick a local pentest model by VRAM budget and context length
- Download GGUF weights of a security model to run locally
- Compare uncensoring methods (SFT, abliteration, LoRA) across models

## Why it’s here

- 23 stars so far today, about 56 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 1 day old and already has 83 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #176.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 3
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 59 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 2

## Stars per day, last 2 days (oldest → newest, today is partial)

2026-09-27 … 2026-09-28: 62, 23

## Spotted in now

- Top new repositories this week: #176

## More in this category

1. **angusdevgo/Seep-Reverse-Lab** — 5.3 · Early signal · Security · Python · +53 stars today, ≈ 111 by evening
   Agent-native reverse engineering workbench for binaries and CWE-602 client-side authorization auditing: unifies Radare2, JADX, Apktool, Frida and IDA via 23 MCP tools with automatic task routing.
   Full card: https://gitnova.dev/en/r/angusdevgo/Seep-Reverse-Lab.md
2. **dagowda/notRDP** — 5.0 · Early signal · Security · C · +11 stars today, ≈ 45 by evening
   A Havoc C2 plugin that creates a hidden alternate Windows desktop, streams it to a browser viewer, and forwards mouse and keyboard input while staying invisible to the target user.
   Full card: https://gitnova.dev/en/r/dagowda/notRDP.md
3. **derv82/wifit3** — 4.8 · Early signal · Security · Python · +7 stars today, ≈ 58 by evening
   Cross-platform USB Wi-Fi auditor in Python: scans networks, captures WPA handshakes and PMKIDs, attacks WPS and WEP via its own userland drivers without aircrack-ng.
   Full card: https://gitnova.dev/en/r/derv82/wifit3.md
4. **newliver666/apk-reverse** — 4.8 · Breakout · Security · Python · +38 stars today, ≈ 242 by evening
   An Agent Skill for Android APK reverse engineering: unpacking, ad removal, dex patching, repacking, and runtime/server analysis. Loaded by an agent (Claude Code, Codex) while it works.
   Full card: https://gitnova.dev/en/r/newliver666/apk-reverse.md
5. **openbao/openbao** — 4.3 · Breakout · Security · Go · +8 stars today, ≈ 43 by evening
   OpenBao is an open-source secrets management system for storing, encrypting, and distributing credentials, keys, and certificates, with dynamic secrets and auditing. A community-governed fork of Vault.
   Full card: https://gitnova.dev/en/r/openbao/openbao.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-28 10:29 UTC, updated every 30 minutes.