ESAA-Security: An Event-Sourced, Verifiable Architecture for Agent-Assisted Security Audits of AI-Generated Code

Researchers have developed ESAA-Security, a new architecture for conducting secure, verifiable audits of AI-generated code using structured agent workflows rather than unstructured LLM conversations. The system creates an immutable audit trail through event-sourcing and produces comprehensive security reports across 26 tasks and 95 executable checks.

• →ESAA-Security addresses security vulnerabilities in AI-generated code through a structured, evidence-based audit process.
• →The architecture separates agent decision-making from system state changes using append-only events for better reproducibility.
• →The system operationalizes security auditing into 26 tasks, 16 security domains, and 95 executable checks.
• →Unlike prompt-based reviews, this approach creates an immutable audit trail with replay-based verification.
• →The framework produces structured vulnerability reports, risk classifications, and remediation guidance by construction.