mcpwn API
    Preparing search index...

    Interface GuardDecision

    The outcome of evaluating one message against the policy.

    interface GuardDecision {
        action: PolicyAction;
        classes: ContentClass[];
        reason: string;
        sanitized?: unknown;
    }
    Index
    action: PolicyAction

    The strongest action any matching rule demanded (block > sanitize > warn > allow), or the policy default when nothing matched.

    classes: ContentClass[]

    Content classes recognised in the message.

    reason: string

    Reason code(s) from the matched rule(s), for the log + finding.

    sanitized?: unknown

    For a "sanitize" decision: the cleaned message JSON (a deep clone; the original is never mutated). Present only when sanitising actually changed something.