Standards, mapped to the incidents behind them
Security and AI-assurance frameworks tell you what to control. CollectSEA shows where each control failed in the real world, so requirements come with evidence a team can read in five minutes.
OWASP GenAI Security Project · 2026 (published December 2025)
OWASP Top 10 for Agentic Applications
The ten most critical security risks for autonomous AI agents that plan, keep memory, call tools and act with delegated authority.
8 of 10 items have documented incidentsOWASP GenAI Security Project · 2026 (published August 2026)
OWASP Top 10 for LLM Applications
The most critical security risks for applications built on large language models.
7 of 10 items have documented incidentsU.S. National Institute of Standards and Technology · Revision 5
NIST SP 800-53 Rev. 5 Security and Privacy Controls
The control catalog used across U.S. federal systems and widely adopted by industry.
17 of 17 items have documented incidentsU.S. National Institute of Standards and Technology · Version 1.1
NIST Secure Software Development Framework (SP 800-218)
Secure software development practices referenced by U.S. federal software attestation requirements.
5 of 5 items have documented incidentsU.S. National Institute of Standards and Technology · AI RMF 1.0 (NIST AI 100-1)
NIST AI Risk Management Framework
A voluntary framework for managing risks of AI systems across design, development, deployment and use.
2 of 2 items have documented incidentsU.S. Cybersecurity and Infrastructure Security Agency · Pledge goals (2024)
CISA Secure by Design Pledge
Seven measurable goals software manufacturers commit to in order to make products secure by design.
5 of 7 items have documented incidentsMITRE · CWE List
MITRE Common Weakness Enumeration
The community-developed list of software and hardware weakness types.
11 of 11 items have documented incidents
How to read these mappings