POL-007 · All channels

Sensitive prompts blocked

Compiled into the runtime gateway and evaluated inline on every prompt, tool call and completion in scope. Owned by AppSec.

Triggers / 30d

76

blocks, masks and escalations

Integrations bound

1

enforced at each connection

Severity

high

owner AppSec

Added latency

7 ms

p99 within the 60 ms budget

Rule definition

Compiled expression

When

  • prompt classified restricted-topic

Then

  • block
  • coach user

Policy as code

apiVersion: truint.ai/v1
kind: RuntimePolicy
metadata:
  id: POL-007
  name: "Sensitive prompts blocked"
  owner: "AppSec"
  scope: "All channels"
spec:
  severity: high
  mode: enforce
  when:
    - "prompt classified restricted-topic"
  then:
    - "block"
    - "coach user"

Governance metadata

Policy ID
POL-007
Owner
AppSec
Scope
All channels
State
Enforcing inline
Catalog version
2026.07.3
Last change
2026-07-22 · approved by AI Council

Bound integrations

Where this rule executes

Recent evaluations

Decisions where this rule fired

11:38:05Merchant Underwriting Agent· emp-20140warn

Screen merchant MRC-9921 for prohibited activity.

11:32:19Wealth Advisory Copilot· emp-20440block

Paste the customer's chat transcript into the public LLM playground.

11:33:15Merchant Underwriting Agent· emp-20847warn

Screen merchant MRC-9921 for prohibited activity.

11:29:53Merchant Underwriting Agent· emp-20158warn

Screen merchant MRC-9921 for prohibited activity.