AgentsSeptember 6, 2026via InfoQ AI/ML
Google Mantis: An Agentic Vulnerability Scanning Harness for Reducing False Positives
Why it matters
Agent autonomy is solving a concrete reliability problem in security—reducing false positives that waste practitioner time. This is agent technology deployed to real work, not a lab demo.
Key signals
- Google open-sourced Mantis framework
- Agentic system handles full vulnerability lifecycle: identify, validate, reproduce, fix
- Designed to reduce false positives and hallucinated vulnerabilities from conventional AI code scanning
- Published September 2026
The hook
Google open-sources Mantis: an AI agent that validates its own vulnerability findings, cutting through hallucinations that plague current scanners.
Google has open-sourced Mantis, an AI-agent framework designed to automate the software vulnerability lifecycle, from identifying and validating vulnerabilities to reproducing and fixing them. Google says it developed Mantis to address the high rate of false positives and hallucinated vulnerabilitie…