Agent Behavior Safety Gate

July 11, 2026

Version updated for https://github.com/NavidBroumandfar/agent-behavior-evals-lab to version v1.2.0.

This action is used across all versions by ? repositories.

Action Type

This is a Composite action.

Go to the GitHub Marketplace to find the latest changes.

What’s Changed

Real-agent fleet calibration (320 records, 3-judge panel), verifier red-team hardening, refusal-under-temptation corpus (local_public_v3), measured eval-awareness reports, laundered-refusal demo record shipped in the offline gate demo. Full details in README and reports/comparisons/.

NavidBroumandfar
GitHub Actions