AI agents make decisions, call tools, and access data autonomously. g0 answers three questions every team must ask before shipping: what agents do you have, what can they access, and can you prove they're under control?
Supported Frameworks
What g0 does
> Discover. Assess. Test. Monitor. Comply.
Static Assessment
1,200+ security rules across 12 domains. Every finding mapped to OWASP, NIST, ISO, and EU AI Act.
Adversarial Testing
4,000+ adversarial payloads with multi-turn adaptive attacks, CVSS scoring, and 20 encoding mutators.
AI Bill of Materials
Every model, tool, agent, and vector DB. CycloneDX 1.6 SBOM export across Python, TypeScript, Java, and Go.
Endpoint Assessment
Discover every AI developer tool installed, which MCP servers are connected, and where the risks are.
Fleet Monitoring
Background daemon for MCP rug-pull detection, AI inventory drift, and fleet-wide visibility.
CI/CD Quality Gate
Fail builds that ship insecure agents. Configurable thresholds with SARIF output for GitHub Code Scanning.
CI/CD
> Fail builds that ship insecure agents.
name: AI Agent Assessment
on: [push, pull_request]
permissions:
security-events: write
contents: read
jobs:
assess:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: '20'
- name: g0 Security Assessment
run: npx @guard0/g0 gate .
--min-score 70
--sarif results.sarif
- uses: github/codeql-action/upload-sarif@v3
if: always()
with:
sarif_file: results.sarifSee your results visually — free.
Push scan results to Guard0 Cloud for architecture visualization, compliance mapping, AI-powered triage, and red team dashboards.
Free for individual developers and small teams (up to 5 projects, 90-day history). When your organization needs governance at scale — that's Guard0 Platform.
Open Source
> Security should be transparent.
g0
ASSESSMENTThe control layer for AI agents. 1,200+ rules, 12 domains, 10 frameworks, 4,000+ attack payloads.
TrustVector
TRUST SCORESEvidence-based evaluation framework with transparent multi-dimensional trust scores.
AIHEM
TRAININGIntentionally vulnerable AI applications for hands-on security training.
> Need enterprise-grade agent governance?