← Back to Agent Chain
📋 AC-6 · Agent Audit
Compliance scoring against EU AI Act, NIST AI RMF, ISO 42001, SOC 2, and OWASP LLM Top 10
Overview

Agent Audit runs automated compliance checks against 5 major frameworks. Each audit produces a score (0–100) with detailed findings, evidence requirements, and remediation guidance.

Supported Frameworks
FrameworkControlsFocus Area
EU AI Act48 requirementsRisk classification, transparency, human oversight
NIST AI RMF42 subcategoriesGovern, Map, Measure, Manage
ISO 4200138 controlsAI management system certification
SOC 2 Type II55 criteriaSecurity, availability, processing integrity
OWASP LLM Top 1010 categoriesPrompt injection, insecure output, supply chain
API Endpoints
Free
MethodEndpointDescriptionAuth
GET/v1/audit/frameworksList compliance frameworks🔓 Free
GET/v1/audit/frameworks/:idFramework details🔓 Free
Billable
MethodEndpointDescriptionAuth
POST/v1/audit/runRun a compliance audit🔑
GET/v1/audit/historyGet audit history🔑
GET/v1/audit/runs/:idGet audit run details🔑
POST/v1/audit/runs/:id/evidenceSubmit manual evidence🔑
POST/v1/audit/schedulesCreate recurring audit schedule🔑
GET/v1/audit/schedulesList audit schedules🔑
DELETE/v1/audit/schedules/:idDelete audit schedule🔑
Quick Start
const audit = await ac.audit.run({ agentId: 'abc123', frameworks: ['eu-ai-act', 'owasp-llm'], evidence: { hasHumanOversight: true, dataRetentionDays: 30, incidentResponsePlan: true } }); // audit.scores = { 'eu-ai-act': 91, 'owasp-llm': 58 } // audit.findings = [{ severity: 'high', control: 'LLM01', ... }]