ai-safety

Repo for vLLM Hook, an vLLM plug-in for programming internal states of models deployed on vLLM

OWASP Foundation web repository

[CCS'24] SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models

AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代建议；可作运行时防护拦截注入与数据外泄 · 中文优先 · 零依赖 · 开源

Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, Antigravity, and any agent supporting the Agent Skills standard.

Ethicore Engine™ is an AI safety, ethics, and compliance platform. This repo consists of the open-source components of Ethicore Engine™ - Guardian SDK; designed to protect your AI applications from prompt injection, jailbreaks, role hijacking, system-prompt extraction, and 100+ additional threat categories through a multi-layer analysis pipeline

LLM alignment jailbreak; a set of instructions for auditing their internal reasoning and uncovering biases

Framework for specifying and proving properties—such as robustness, fairness, and interpretability—of machine learning models using Lean 4.

Utterly unelegant prompts for local LLMs, with scary results.

Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo: anton.securelayer7.net

[DEPRECATED] Moved to microsoft/agent-governance-toolkit

An evidence-led, eight-locale LLM playbook: a transferable core, the Codex flagship track, and adapters for ChatGPT, Claude Code, Gemini, DeepSeek, and Grok.

Static analysis for AI agent configs, tool descriptions, and system prompts — catches vague tool descriptions, missing stop conditions, and schema gaps before they reach runtime. Zero-LLM, deterministic checks, built for CI.

Claude Code best practices applied to application design. Interactive HLD/LLD visualizations, a DB-governed implementation example, and the same primitives as a runnable agent: the Governed Agent. LLM-agnostic, DB-governed, GDPR-ready.

[L0 CONSTITUTION] arifOS — constitutional MCP kernel. Law, identity, F1–F13, VAULT999. Judges but never executes. DITEMPA BUKAN DIBERI.

Инициатива, посвященная безопасности агентов на базе искусственного интеллекта

Biologically-grounded adversarial training platform: cyclic Wake/Dream/Nightmare/Compress phases that accumulate model robustness without catastrophic forgetting. Dockerized, EU AI Act compliance reporting.

Easy to use LLM Prompt Injection Detection and Prompt Input Sanitization / Detector Python Package with support for local models, API-based safeguards, safeguard for tool calls, and LangChain guardrails.

AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking curves, compare variants with evidence — not vibes.