Skip to content
Guard0

g0Background Check for AI Agents

You wouldn't hire someone without a background check. Why would you deploy an AI agent without one?

$ npx @guard0/g0 scan .
GitHubDocsnpmStart Free on Guard0 →
LangChain
OpenAI
Anthropic
CrewAI
AWS Bedrock
Vercel AI
Salesforce
1,200+
Security Rules
1,200+
Attack Payloads
341+
ClawHavoc IOCs
11
Framework Parsers
What g0 does

Every background check answers three questions

You wouldn't hire someone without a background check.

Point g0 at any repo. It discovers every agent, maps every tool, and scores 12 security domains against OWASP, NIST, ISO, and EU AI Act. Every finding tells you what's wrong, where it is, and how to fix it.

$ g0 scan ./my-agent
LangChainLangChain
OpenAIOpenAI
AnthropicAnthropic
CrewAICrewAI
AWS BedrockAWS Bedrock
Vercel AIVercel AI
SalesforceSalesforce
+5 more
g0 scan ./my-banking-agent
g0 v2.4.1 | Framework: langchain (+mcp)
Files: 14 | Agents: 2 | Tools: 4 | Prompts: 2
Goal Integrity60
5 issues
Tool Safety78
4 issues
Identity & Access45
6 issues
Data Leakage82
3 issues
Code Execution52
6 issues
Memory & Context71
3 issues
Supply Chain91
1 issues
Human Oversight88
1 issues
MCP Security55
4 issues
Cascading Failures73
2 issues
CRITICALShared memory between users
main.py:8 | OWASP:ASI07 | Fix: Isolate memory per user_id
HIGHSystem prompt has no scope boundaries
main.py:21 | OWASP:ASI01 | NIST:GV-1.1
HIGHDatabase tool without input validation
tools.py:34 | Fix: Add parameterized queries
MEDIUMUnpinned model version
config.yaml:3 | OWASP:ASI07 | Fix: Pin to specific version
Overall:C21 findings | 2 Critical | 5 High | 6 Medium

And that's not all

Everything else the background check covers.

AI Bill of Materials

Every agent, model, tool, and dependency. JSON export for automation.

Map Execution Flows

Trace data from user input to code execution. Find toxic flows.

Gate Your CI/CD

Fail builds on critical findings. Exit codes, SARIF output, policy-as-code.

Run the Daemon

Background monitoring. Skill drift alerts. MCP config change detection.

Break Before Production

1,200+ adversarial payloads. 4-level progressive judge. CVSS scoring.

Interactive Shell

Explore findings interactively. Full security assessment REPL.

g0 scans your code. Guard0 governs your org.

Start with the CLI. Graduate to the platform. Scale to the enterprise.

g0 CLI

Open Source
  • Scan any repo. Offline-first.
  • Red-team any agent endpoint.
  • Audit every MCP server.
  • Gate CI/CD on critical findings.
$ npx @guard0/g0 scan .

Guard0 Cloud

Free Tier
  • Dashboard for all scan results.
  • Governance control tracking.
  • Runtime control.
  • Scales with early-stage teams.
Start Free

$0 to get started

Guard0 Enterprise

Custom
  • Full agent inventory. Org-wide.
  • Policies. Runtime control. Kill switch.
  • Compliance proof for auditors.
  • On-prem. SIEM integration.