Security AI projects by category

AI-assisted tools and workflows for penetration testing, validation, and exploit path analysis.

Resources for adversarial evaluation of systems, models, applications, and security controls.

Projects that help researchers discover, validate, report, or prioritize bug bounty findings.

Tools and research artifacts used to investigate weakness classes and exploitable conditions.

Security AI resources focused on web, product, and application security workflows.

Security testing, validation, and governance for large language model applications.

Security resources for autonomous agents, tool use, delegation, and action-bearing AI systems.

Code analysis, secure code review, repository intelligence, and remediation assistance.

Agentic systems that can plan, call tools, inspect results, and perform security tasks.

Frameworks, standards, and reference architectures for security AI work.