{"id":"google-model-armor","name":"Model Armor","maker":"Google Cloud","url":"https://cloud.google.com/security/products/model-armor","docs":"https://docs.cloud.google.com/model-armor/overview","summary":"A Google Cloud service that screens prompts and responses for prompt injection, jailbreaks, sensitive data and malicious links.","details":"Applications call methods that sanitise a user prompt or a model response against a template of filters for prompt injection and jailbreaks, sensitive data, malicious URLs and harmful content, including text in documents. It can only log findings or also return a block verdict. It needs a Google Cloud account and is not open source.","open_source":false,"hosted":true,"verified":"2026-11-15","category":"safety","category_name":"Guardrails and security","page":"https://modelmoot.com/tools/google-model-armor","reviewed":"2026-11-15","checked":{"at":"2026-11-15T15:07:43.409Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}