Detections

Explore public detection logic contributed by the community across SIEM and rule languages.

1 detection

Detects potential zero-click LLM prompt injection attacks against Microsoft 365 Copilot. The rule correlates Microsoft 365 Copilot activity involving external/untrusted URLs or domains with recent inbound email activity to the same user. This pattern is designed to identify scenarios where an attacker leverages an inbound email to trigger a Copilot interaction with malicious external content, potentially leading to unauthorized data access or exfiltration.
GlassDiceBearhttps://www.dicebear.comhttps://creativecommons.org/publicdomain/zero/1.0/„Glass” (https://www.dicebear.com) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)
Syed Usfar Wasim@nCD24
GlassDiceBearhttps://www.dicebear.comhttps://creativecommons.org/publicdomain/zero/1.0/„Glass” (https://www.dicebear.com) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)
Detections.ai Community
5 months ago
10027