AgentGuard: Zero-Trust Security Foundation for AI Agents
☆156Oct 31, 2026Updated this week
Alternatives and similar repositories for AgentGuard
Users that are interested in AgentGuard are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- VioHawk: Detecting Traffic Violations of Autonomous Driving Systems through Criticality-guided Simulation Testing☆15Aug 5, 2024Updated 2 years ago
- SCTrans: Constructing a Large Public Scenario Dataset for Simulation Testing of Autonomous Driving Systems☆28Mar 5, 2026Updated 7 months ago
- Hermes is an automated security tool written in Python designed to discover Cross-Site Scripting (XSS) vulnerabilities in web application…☆10Aug 22, 2025Updated last year
- The source code of [Sec'25] Make Agent Defeat Agent: Automatic Detection of Taint-Style Vulnerabilities in LLM-based Agents☆111Apr 13, 2026Updated 6 months ago
- Search for top security papers with one click! Visit https://lzher.github.io/security-paper-db/☆14Jul 17, 2026Updated 3 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆18Nov 19, 2025Updated 11 months ago
- Whitzard (白泽) — WhitzardAgent's CyberGym write-up (68.9%, GLM-5.1-FP8)☆29Aug 13, 2026Updated 2 months ago
- SafeHarness: Security-Aware Harness Architecture for Safe AI Agent Deployment☆18May 12, 2026Updated 5 months ago
- Run AI agents safely on your local machine☆41May 24, 2026Updated 5 months ago
- ☆39Jun 13, 2026Updated 4 months ago
- 回声Echo：AI文案助手☆10May 6, 2023Updated 3 years ago
- HouseFuzz: Service-Aware Grey-Box Fuzzing for Vulnerability Detection in Linux-Based Firmware☆23May 31, 2026Updated 5 months ago
- VulnGym: A Real-World, Project-Level Vulnerability Benchmark for White-Box Vulnerability-Hunting Agents☆361Oct 8, 2026Updated 3 weeks ago
- The first multi-level safety evaluation platform for OpenClaw-style AI agents.☆38May 27, 2026Updated 5 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- 自动化渗透测试框架。它结合了现代 AI 技术（RAG、ReAct）与传统安全工具，能够按照标准的渗透测试流程（信息收集 -> 漏洞探测 -> 漏洞利用 -> 权限维持 -> 横向移动）自动执行任务。☆19Mar 5, 2026Updated 7 months ago
- Let's Qitos! A torch-like agent-native framework for researchers.☆46Sep 9, 2026Updated last month
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆970Jun 2, 2026Updated 4 months ago
- Data Analysis of the results of llmail-inject challenge☆12Jul 1, 2025Updated last year
- ☆49Dec 9, 2025Updated 10 months ago
- The official implementation of the paper "AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?"☆89May 19, 2026Updated 5 months ago
- Official codebase for the paper "Auditing Agent Harness Safety"☆57Oct 12, 2026Updated 2 weeks ago
- ☆32Jan 30, 2026Updated 9 months ago
- 向TSRC投稿的文章，对应的pdf，代码和思维导图☆21Sep 18, 2020Updated 6 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- 本仓库整理公开披露的 OpenClaw 恶意 / 可疑 Skills 样本，并对其进行分类、分级与风险说明，供安全研究、平台治理和风险检测使用。☆21Mar 16, 2026Updated 7 months ago
- ☆16Sep 14, 2026Updated last month
- ☆26Mar 27, 2026Updated 7 months ago
- CyberGym-E2E is a large-scale benchmark built from real-world vulnerabilities in widely used open-source projects to evaluate AI agents' …☆92Oct 7, 2026Updated 3 weeks ago
- AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assess…☆67Updated this week
- xAST评价体系，让安全工具不再“黑盒”. The xAST evaluation benchmark makes security tools no longer a "black box".☆495May 21, 2026Updated 5 months ago
- POC管理平台已集成公开POC仓库内容,可自行添加POC到平台实现集中管理,快速搜索,验证☆35Aug 6, 2026Updated 2 months ago
- A.S.E (AICGSecEval) is a repository-level AI-generated code security evaluation benchmark developed by Tencent Wukong Code Security Team.☆666May 25, 2026Updated 5 months ago
- [ICML 2026] AutoControl Arena: Frontier AI Risk Auto-Discovery Platform☆92Oct 13, 2026Updated 2 weeks ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- [ICLR'26 Oral] RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments☆66Feb 9, 2026Updated 8 months ago
- "他山之石、可以攻玉"：复旦JADE团队发布的大模型测评与治理系列☆534Updated this week
- Log all keyboard and terminal input/output for any app 记录任意程序的键盘输入和终端输入输出☆24Jul 14, 2026Updated 3 months ago
- Responsible Robotic Manipulation☆17Aug 31, 2025Updated last year
- Official Code for Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification.☆21Jul 1, 2026Updated 3 months ago
- Advanced AI-Powered Exploitation Framework | CVE-2025-4664 & CVE-2025-2783 & CVE-2025-2857 & CVE-2025-30397 |☆18Jan 18, 2026Updated 9 months ago
- A curated list of awesome resources about LLM supply chain security (including papers, security reports and CVEs)☆108Jan 20, 2025Updated last year