Anthropic Launches Free AI Security Scanner

Anthropic introduced OSS Scanner on October 8, 2026, a free service that uses AI models, including Claude Mythos, to perform periodic security audits on eligible open-source projects. Maintainers can opt in by submitting a pull request on GitHub, allowing the service to scan codebases in isolated environments.

The scanner generates vulnerability reports without human review or triage. Anthropic reported that testing across 48 projects resulted in 88% of findings meeting its coordinated disclosure standards.