News
The OWASP GenAI Security Project publishes a standard to control AI agents at runtime.
The Agent Control Standard provides for a separate Guardian that authorizes, refuses or modifies actions before their execution.
OpenTelemetry traces and an AgBOM inventory of models and tools complete the system.
According to the author, the v0.1.0 reference implementation only evaluates two of 19 hooks live.
By default, a Guardian failure lets the host continue the actions.