BizKitHub
AI_PI_DETECTED

Prompt-injection patterns detected in agent input

WarningAIAffects operatorsRetry: not retryable
Text sent to the AI agent (a ticket body or tool result) contained suspicious patterns such as instructions to ignore previous rules, role-play directives or fake system messages. The request still went ahead on a sanitised copy. Repeated detections from one sender or organisation may indicate a deliberate attempt to manipulate the agent and are worth reviewing.

Likely causes

  • A ticket body or other agent input contained text that resembles instructions aimed at the AI (for example "ignore previous instructions").
  • Input contained fake system messages, role-play directives, or control-token sequences.

How to resolve

  1. 1

    No immediate action is needed; the AI call proceeded on a sanitised copy of the input.

  2. 2

    Review the triggering issue and sender if detections repeat for the same organisation or sender.

  3. 3

    Consider blocking or marking the sender as spam if the attempts are clearly malicious.

Where you will see it

The code tags entries in the admin Log viewer, where you can filter by it and open individual occurrences. Codes logged as error or critical can also trigger a technical notification e-mail with the code in the subject:

Notification subject
[AI_PI_DETECTED] [ai] …