FlagThis

References :

• CSO Online: Security researchers circumvent Microsoft Azure AI Content Safety
• www.microsoft.com: AI jailbreaks: what they are and how they can be mitigated
• learn.microsoft.com: AI Text Moderation should block requests that involve violence or hate speech — for example, instructions for making a bomb or a request to generate a sexist cartoon.

Classification:

• HashTags: #AzureAI #ContentSafety #Vulnerability
• Company: Microsoft
• Target: Azure AI
• Product: Azure AI
• Feature: Content Safety
• Type: Vulnerability
• Severity: Medium