Detection rules

Explore published rules with transparent provenance, licensing, and ATT&CK mappings.

11,424
detections

Search detections

Filters

Showing 30 of 11,424

Detects M365 Copilot jailbreak attempts through prompt injection techniques including rule manipulation, system bypass commands, and AI impersonation requests that attempt to circumvent built-in safety controls. The detection searches exported eDiscovery prompt logs for jailbreak keywords like "pretend you are," "act as," "rules=," "ignore," "bypass," and "override" in the Subject_Title field, assigning severity scores based on the manipulation type (score of 4 for amoral impersonation or

T1685

Written by: Rod SotoAttributed by Splunk security content
Licence: Apache License 2.0
Published: Oct 8, 2026

MediumSplunk security content

M365 Copilot Information Extraction Jailbreak Attack

Detects M365 Copilot information extraction jailbreak attacks that attempt to obtain sensitive, classified, or comprehensive data through various social engineering techniques including fictional entity impersonation, bulk data requests, and privacy bypass attempts. The detection searches exported eDiscovery prompt logs for extraction keywords like "transcendent," "tell me everything," "confidential," "dump," "extract," "reveal," and "bypass" in the Subject_Title field, categorizing each

T1685

Written by: Rod SotoAttributed by Splunk security content
Licence: Apache License 2.0
Published: Oct 8, 2026

MediumSplunk security content

M365 Copilot Impersonation Jailbreak Attack

Detects M365 Copilot impersonation and roleplay jailbreak attempts where users try to manipulate the AI into adopting alternate personas, behaving as unrestricted entities, or impersonating malicious AI systems to bypass safety controls. The detection searches exported eDiscovery prompt logs for roleplay keywords like "pretend you are," "act as," "you are now," "amoral," and "roleplay as" in the Subject_Title field.

T1685

Written by: Rod SotoAttributed by Splunk security content
Licence: Apache License 2.0
Published: Oct 8, 2026

InformationalSplunk security content

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 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.

T1685

Written by: Rod SotoAttributed by Splunk security content
Licence: Apache License 2.0
Published: Oct 8, 2026

Reference	Class	Cited by
cloud.google.com/vertex-ai/generative-ai/docs/multimodal/request-response-logging	Product documentation	Only this detection cites it
www.elastic.co/docs/reference/integrations/gcp_vertexai	Product documentation	9

Detection rules

Description

Detection logic

Detection requirements

Known benign triggers

MITRE ATT&CK mappings

References

From the source

Licence

Authorship

Detection rules