
secure-agent-playbook
OWASP Secure Agent Playbook Project

OWASP Secure Agent Playbook Project

Hands-on AI security learning platform with intentionally vulnerable LLM applications. Explore OWASP Top 10 for LLMs through interactive pizza shop…

OWASP project defining an AI Bill of Materials (AIBOM) standard to document AI/ML components, dependencies, and supply chain risks for AI security…

DonkAI is a hands-on lab for the OWASP Top 10 for LLM Applications (2025) - no real LLM required.

Automated SBOM-to-VEX pipeline using a secure multi-agent AI system to analyze CVEs, reason about exploitability, and generate signed CycloneDX VEX…

The AI Security Verification Standard (AISVS) focuses on providing developers, architects, and security professionals with a structured checklist to…

Coordination structure for AI security standards and guidelines, reducing fragmentation and providing clear guidance for securing AI systems across…

Open standard for documenting security-relevant metadata of AI models, including training data provenance, PII risk, known vulnerabilities, and…

SecureML - Securing and Watermarking AL models

Security standard for agent skills, providing guidelines and best practices to secure AI-driven autonomous agents in cloud and API environments.

Intentionally vulnerable machine learning model for hands-on security training. Explore common ML vulnerabilities, adversarial attacks, and defensive…

The Governed Agentic AI Operating System — Rust + Tauri 2.0 | 65 crates, 658 commands, 84 pages, 5,029 tests, 10/10 OWASP

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt…

Open-source interactive security awareness training library with 130+ SCORM exercises covering phishing, vishing, BEC, MFA fatigue, and OWASP AI/LLM…

Open-source cross-modal and multimodal prompt injection test suite. 250,000+ attack payloads across text, image, document, and audio modalities.…

Research repository documenting LLM generalization ceilings in code security vulnerability detection, with cross-evaluation across synthetic and…

Free security-baseline rule for Claude Code, Codex, and Cursor: treats MCP tool descriptions as untrusted input (OWASP MCP Top 10 MCP03,…