Stars
The community's most comprehensive, continuously-updated index of research on Large Language Models for software vulnerability detection — papers across function-level, repository-level, agentic, a…
Multi-tier firewall for AI agents — blocks prompt injections, jailbreaks, and scope violations. Local tiers first; LLM judge only when uncertain.
Kaggle competition workspace for AI agent security and multi-step tool attack detection.
The batteries-included agent harness.
lightweight system-level observability for AI Agents
AI agents that think must never act. Open-source security framework with composable modules for safe autonomous AI.
MCPSafetyScanner - Automated MCP safety auditing and remediation using Agents. More info: https://www.arxiv.org/abs/2504.03767
Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.
Security scanner for AI agent skills and MCP tool bundles — prompt injection, IOC matching, malware detection, ML classifier
TRACE is a practical agentic jailbreak framework that leverages task decomposition, task-aware disguising scenarios and adaptive self-evolution to investigate emerging security risks of LLM-based a…
Yuque MCP Server - Model Context Protocol server for Yuque API
[NeurIPS 2025] Official repository of RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation,…
CodeQL: the libraries and queries that power security researchers around the world, as well as code scanning in GitHub Advanced Security
The source code of [Sec'25] Make Agent Defeat Agent: Automatic Detection of Taint-Style Vulnerabilities in LLM-based Agents
AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents
🧱 easy fast local-first microVM runtime and library
AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.
Hey folks, this is a repository for papers on LLM for Vuln. Detection area
Hey folks, this is a repository for papers on LLM for Vuln. Detection area
C++ Parallel Computing and Asynchronous Networking Framework
🤙 Easy replacement for LaTeX Beamer! 🥂 custom Marp templates with a selection of over a dozen themes
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
将文件隐写进MP4/MKV文件中 （Embed files into MP4/MKV files.）