Messaging Policies

Managed Mode reference. You do not configure these policies. They are enforced automatically for applicable ActionKinds.

Trigger example (derived from the managed catalog)

Messaging policies can trigger when outbound content includes prohibited data (secrets/credentials) or when review is required before sending.

Example ActionKind where messaging policies apply: messaging.send

Common required context fields: message_body

Example decision

WARN responses include an approval_token. BLOCK responses do not.

json

{
  "status": "WARN",
  "decision_id": "dec_...",
  "approval_token": "appr_...",
  "reasons": [
    "Messaging content requires review"
  ]
}

json

{
  "status": "BLOCK",
  "decision_id": "dec_...",
  "reasons": [
    "Block outbound messages that contain secrets/credentials or sensitive internal data."
  ]
}

Resolution

Apply the remediation specified by the policy that fired, then re-validate.

Summary	Severity	Applies to	Required context	Approval	Remediation
Block outbound messages that contain secrets/credentials or sensitive internal data.	BLOCK	messaging.send, messaging.webhook	message_body	—	Redact sensitive tokens. Replace with references. Ensure destinations are allowlisted.

Legal & Responsibility Notice

Summary

Informational only

Provided for general guidance. Not legal, compliance, security, or professional advice.

You control implementation

You are responsible for policies, prompts, integrations, workflows, and regulatory requirements.

Liability limitation

To the maximum extent permitted by law, the company disclaims liability for losses arising from use of this documentation or implementations based on it.