awesome-security-vul-llm
xu-xiang/awesome-security-vul-llm本项目通过大模型联动爬虫，检索Github上所有存有有价值漏洞信息与漏洞POC或规则信息的项目，并自动识别项目的目录结构、Readme信息后进行总结分析并分类，所汇总的项目可以帮助安全行业从业者收集漏洞信息、POC信息、规则等。
ai-securitycurated-resourceseducation+2
xu-xiang/awesome-security-vul-llm本项目通过大模型联动爬虫，检索Github上所有存有有价值漏洞信息与漏洞POC或规则信息的项目，并自动识别项目的目录结构、Readme信息后进行总结分析并分类，所汇总的项目可以帮助安全行业从业者收集漏洞信息、POC信息、规则等。
crucible-security/cruciblepytest for AI agents - Autonomous red-teaming, behavioral monitoring & security testing for LLM agents
kryptsec/oasisOpen-source AI security benchmarking CLI. Measure how AI models perform offensive security tasks with MITRE ATT&CK analysis and KSM scoring.
pie-script/llm-agent-testbedAn empirical security testbed evaluating prompt injection, confused-deputy vulnerabilities, and tool-calling defenses in LLM agents.
fallen-angel-systems/fas-judgement-ossOpen-source prompt injection attack console. Test AI security by firing categorized attacks at any endpoint.
mickmicksh/chub-supply-chain-pocSilent dependency injection through AI documentation pipelines. 240 isolated Docker runs proving Context Hub's zero-sanitization MCP server lets…
owasp/secretsifterOWASP Incubator project: detects credentials exposed in browser-delivered content (JavaScript, config responses, live traffic).
owasp/www-project-top-10-for-large-language-model-applicationsOWASP Top 10 for Large Language Model Apps (Part of the GenAI Security Project)
owasp/secure-agent-playbookOWASP Secure Agent Playbook Project
owasp/owasp-top-10-neocloud-and-ai-data-center-security-risksOWASP framework cataloging the top 10 security risks in neocloud and AI data center infrastructure, covering hardware, networking, isolation,…
owasp/owasp-aibomOWASP project defining an AI Bill of Materials (AIBOM) standard to document AI/ML components, dependencies, and supply chain risks for AI security…
owasp/donkaiDonkAI is a hands-on lab for the OWASP Top 10 for LLM Applications (2025) - no real LLM required.
owasp/robotics-security-testing-guideOWASP guide defining a standardized penetration testing methodology for humanoid, industrial, and autonomous robots, covering ROS/ROS2, DDS, CAN bus,…
owasp/agentic-evidenceOWASP reference project for agentic AI security evidence: correlates agent execution, identity, tool calls, and authorization decisions into…
owasp/llmsecOWASP project focused on security for large language model applications, covering LLM-specific risks, testing guidance, and mitigation practices.
owasp/sbom-vex-taint-analysisAutomated SBOM-to-VEX pipeline using a secure multi-agent AI system to analyze CVEs, reason about exploitability, and generate signed CycloneDX VEX…
owasp/ai-threat-modelerOWASP project for AI-assisted threat modeling, helping teams identify, analyze, and document security threats and mitigations in system designs.
owasp/aisvsThe AI Security Verification Standard (AISVS) focuses on providing developers, architects, and security professionals with a structured checklist to…