Detecting and analyzing prompt abuse in AI tools

This second post in our AI Application Security series is all about moving from planning to practice. AI Application Series 1: Security considerations when adopting AI tools established how AI adoption expands the attack surface and our threat-modelling guidance on the Microsoft security blog...

Detecting and analyzing prompt abuse in AI tools

This second post in our AI Application Security series is all about moving from planning to practice. AI Application Series 1: Security considerations when adopting AI tools established how AI adoption expands the attack surface and our threat-modelling guidance on the Microsoft security blog...

CVE-2025-48597

In multiple locations, there is a possible way to trick a user into accepting a permission due to a tapjacking/overlay attack. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is not needed for exploitation...

Exploit for CVE-2025-64495

CVE-2025-64495-POC Open WebUI vulnerable to Stored DOM XSS via...

CVE-2022-22762

Under certain circumstances, a JavaScript alert or prompt could have been shown while another website was displayed underneath it. This could have been abused to trick the user. This bug only affects Firefox for Android. Other operating systems are unaffected.. This vulnerability affects Firefox ...