safety

Open repos and models their makers tagged safety, most starred first. The same for everyone.

Developer toolsRepo

destructive_command_guard

A fast Rust safety hook that blocks destructive shell, git, and filesystem commands before AI coding agents run them. 50+ security packs (databases, Kubernetes, Docker, cloud, Terraform), heredoc/inline-script scanning, CI scan mode, and explain mode; works with Claude Code, Codex, Gemini, Copilot, Cursor, and more.

  • 6.4k
  • Rust
  • 2 d ago
Security and privacyRepo

latte

☕ Latte: the safest & truly intuitive templates for PHP. Engine for those who want the most secure PHP sites.

  • 1.3k
  • PHP
  • 1 d ago
netteTake it
Security and privacyRepo

Sefinek-Blocklist-Collection

🌍 A repository of blocklists for various DNS servers, featuring over 100 links and more than 6 million domains. Additionally, you can use our personalized Blocklist Generator to customize content filtering according to your individual needs, giving you full control over what should be blocked on your network.

  • 779
  • JavaScript
  • 13 h ago
sefinekTake it
Security and privacyRepo

forms

📝 Generating, validating and processing secure forms in PHP. Handy API, fully customizable, server & client side validation and mature design.

  • 532
  • PHP
  • 23 h ago
netteTake it
Security and privacyRepo

ai-jailbreaks

AI jailbreaks: 35 paste-ready AI jailbreak prompts for 25+ frontier and open-weight models - system prompts, AGENTS.md specs, and Ollama Modelfiles. Built for AI security research and red-team testing.

  • 453
  • 4 wk ago
Security and privacyRepo

NewPass

🔐 NewPass is a free and open source password manager which will allow you to generate and store your passwords securely, saving them locally and encrypting them on your phone's memory

  • 263
  • Java
  • GPL-3.0
  • 2 y ago
6eeroTake it
GitHubRepo

CKA-Agent

[ICML 2026 & ICLR 2026 AIWILD] Official Implementation of the CKA-Agent, "The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search".

  • 217
  • Python
  • AGPL-3.0
  • 6 mo ago
Graph-COMTake it
Security and privacyRepo

MMTrustEval

A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)

  • 177
  • Python
  • CC-BY-SA-4.0
  • 17 mo ago
thu-mlTake it
AI on my own machineRepo

TruthX

Code for ACL 2024 paper "TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space"

  • 145
  • Python
  • GPL-3.0
  • 3 y ago
ictnlpTake it
Developer toolsRepo

dsh-permission-rules

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.

  • 138
  • TypeScript
  • Apache-2.0
  • 1 d ago
PerryLinkTake it
AI agentsRepo

MLA-Trust

A toolbox for benchmarking Multimodal LLM Agents trustworthiness across truthfulness, controllability, safety and privacy dimensions through 34 interactive tasks

  • 64
  • Python
  • MIT
  • 11 mo ago
thu-mlTake it
GitHubRepo

Virus

This is the official code for the paper "Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation"

  • 56
  • Python
  • Apache-2.0
  • 22 mo ago
git-dislTake it
Search GitHub and Hugging Face for safety

Get , open it once and sign in. Then come back here and press the button again.

safety: open source repos and models on Take My Repo