AI security agent that finds vulnerabilities in AI-built apps, prepares fixes, and verifies the live app after deployment
Security scanner for AI-generated code that catches secrets, CVEs, and OWASP vulnerabilities in under 30 seconds and auto-fixes with GitHub PRs
Stage
Startup
Not given
Founded
2026
Not given
Based in
US
Not given
Pricing model
Free trial
Freemium
Pricing
Free scan with no card required. 7 days free trial with card, then $80/month USD. One organization with up to three included full-access people. $20/month per additional full-access person.
Free tier for public repositories with 3 scans per hour; paid plans available for private repositories and higher scan limits
Key features
Continuous attack-surface mapping of exposed endpoints, services, and certificates
Vulnerability investigation with confirmed evidence and real impact explanation
Automatic fix pull requests on separate GitHub branches
Live verification that vulnerabilities are actually closed after deployment
Team notifications via Slack, Discord, and email with weekly summaries
Detection of exposed endpoints, leaked keys, open buckets, and injection paths
Domain ownership verification via DNS TXT record
Live retest to confirm vulnerability closure after fix deployment
Plain-English vulnerability titles with technical details in records
Multi-domain support on single surface map
Secret detection with 200+ credential patterns
CVE vulnerability scanning via OSV.dev
OWASP Top 10 coverage
Automated GitHub PR remediation
AI-powered fix explanations
Supply chain security analysis
API security scanning
CLI and CI/CD integration
Read-only ephemeral scanning
Scans complete in under 30 seconds
What makes it different
Verifies vulnerabilities are actually fixed by testing the live deployed app after fixes ship
Prepares actionable fix pull requests you review and control before deployment
Designed specifically for AI-built applications that ship vulnerable code by default
Continuously monitors your changing app surface and checks again automatically
Shows evidence behind every finding so you can verify the work yourself
Tuned detection rules for AI-generated code failure modes rather than generic vulnerability patterns
Specific vulnerability detection for each major AI coding tool including Copilot, Cursor, and Claude
Automated remediation with GitHub PR creation requiring no manual triage
Full scans in under 30 seconds with code never stored or used for training
Fills security gaps that existing tools like Snyk and Semgrep were not designed for
Zoltra
ZenVeil