Sunturai
Back to results
InformationalSplunk security contentRod Soto

M365 Copilot Agentic Jailbreak Attack

Detects agentic AI jailbreak attempts that try to establish persistent control over M365 Copilot through rule injection, universal triggers, response automation, system overrides, and persona establishment…

Description

Detects agentic AI jailbreak attempts that try to establish persistent control over M365 Copilot through rule injection, universal triggers, response automation, system overrides, and persona establishment techniques. The detection analyzes the PromptText field for keywords like "from now on," "always respond," "ignore previous," "new rule," "override," and role-playing commands (e.g., "act as," "you are now") that attempt to inject persistent instructions. The search computes risk by counting distinct jailbreak indicators per user session, flagging coordinated manipulation attempts.

Detection logic

Detection requirements

Platform
ContainersESXiIaaSLinuxmacOSNetwork DevicesWindows

The rule states no platform. This is derived from the ATT&CK technique it maps to.

Log source category
m365_exported_ediscovery_prompts

Known benign triggers

  • Legitimate users discussing AI ethics research, security professionals testing system robustness, developers creating training materials for AI safety, or academic discussions about AI limitations and behavioral constraints may trigger false positives.

Detections can measure how the public catalogue is used — which detections people look for, and which pages bring them here. It sets a cookie that recognises this browser for 180 days. It is never linked to an account and never follows you to other sites. Privacy notice