pattern detail
external-automation-standing
Restricts outbound automations such as webhooks, mass messaging, and third-party workflow execution unless the workflow is already sanctioned.
Pattern analysis
doctrinal basis
Restricted engagement zones and escalation of force, translated into outbound automation controls.
Use the summary here for context, then inspect the YAML or related patterns for the concrete rule path.
What it catches
- Prompt injection that tries to exfiltrate data through a webhook or outbound API call.
- Abuse of CRM or email tooling to send unauthorized bulk communications.
- Agent attempts to stand up a new external automation path without operator review.
Related patterns
policy yaml
The downloadable policy stays available below, but the inline YAML now wraps cleanly for narrow screens.
name: external-automation-standing
version: 0.1.0
doctrinal_basis: >-
Restricted engagement zones and escalation of force principles adapted to
outbound automation surfaces.
description: Standing controls for outbound automations and third-party execution.
rules:
- id: deny-new-webhook-destinations
applies_to:
action_class:
- external.webhook.create
- external.webhook.update
decision: deny
reasoning: >-
Creating or retargeting webhook destinations is denied by standing policy.
- id: escalate-mass-messaging
applies_to:
action_class:
- external.email.bulk_send
- external.sms.bulk_send
decision: escalate
escalation:
requires: human_approval
via: communications-ops
reasoning: >-
Bulk outbound communication requires operator approval and campaign review.