{"id":"azure-prompt-shields","name":"Azure AI Content Safety Prompt Shields","maker":"Microsoft","url":"https://learn.microsoft.com/en-us/azure/ai-services/content-safety/concepts/jailbreak-detection","summary":"A service in Azure AI Content Safety that detects prompt injection and jailbreak attempts in user input and documents.","details":"Called through a REST API or Azure SDKs, it screens direct user prompts and indirect attacks hidden in documents before they reach a model. It needs an Azure account and is a closed commercial service.","open_source":false,"hosted":true,"verified":"2026-11-15","category":"safety","category_name":"Guardrails and security","page":"https://modelmoot.com/tools/azure-prompt-shields","reviewed":"2026-11-15","checked":{"at":"2026-11-15T13:03:28.711Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}