AI Defense Matrix Catalog

Azure AI Content Safety

Visit official site ↗

Overview

Product details compiled from public sources, each with a citation.

Vendor
Microsoft1
Description
Microsoft content-safety service for generative AI that uses Prompt Shields to detect and block jailbreaks and indirect prompt injection, and filters prompts and responses across harm categories.1
Deployment
SaaS1
Status
Active1
Compliance
SOC 2 Type 2, ISO 27001, ISO 27017, ISO 27018, ISO 277013 (company-level, see Methodology)

Matrix Coverage

Where this product defends, by asset class and NIST CSF function. The Coverage column shows whether each asset is Primary, Secondary, or Adjacent to what the product does. The table omits empty rows and columns.

Asset class ProtectDetect Coverage
Runtime AI Data Primary 2

Framework Relevance

These frameworks include controls relevant to the asset classes Azure AI Content Safety defends. This is an editorial inference from the AI Defense Matrix asset-level crossmap, not a statement that Microsoft implements these controls or is certified against them.

Expand Collapse
Framework Asset class Relevant controls
NIST IR 8596 Runtime AI Data Prompts (runtime); inference data
CSA AI Controls Matrix Runtime AI Data Data Security and Privacy Lifecycle Management; Application and Interface Security
ISO 42001 Runtime AI Data A.7 Data for AI systems; A.8 Information for interested parties
Google SAIF Runtime AI Data Expand AI red-teaming; runtime input and output safety; prompt defense
SANS Critical AI Security Guidelines Runtime AI Data Model I/O Handling (sanitize, validate, and filter inputs and outputs; segregate user and system prompts; multilayered prompt-injection defense); Conventional Security Controls (protect augmentation and RAG data with vector-store access controls and validation); Data Minimization and Obfuscation (limit sensitive prompt content; context-window management); Limit Model Behavior (AI guardrails)
MITRE ATLAS Runtime AI Data AML.T0051 LLM Prompt Injection; AML.T0054 LLM Jailbreak; AML.T0056 Extract LLM System Prompt
OWASP AI Exchange Runtime AI Data Input threats: prompt injection, adversarial inputs, evasion; runtime threats: RAG poisoning, memory tampering
OWASP LLM Top 10 Runtime AI Data LLM01 Prompt Injection; LLM02 Sensitive Information Disclosure; LLM08 Vector and Embedding Weaknesses; LLM05 Improper Output Handling
OWASP Agentic Security Top 10 Runtime AI Data ASI06 Memory & Context Poisoning; ASI01 Agent Goal Hijack (via prompt injection in runtime inputs)

Provenance

Last sourced 2026-06-09.

Expand Collapse

Sources

  1. Azure AI Content Safety
    Vendor source accessed 2026-06-09
  2. Prompt Shields in Azure AI Content Safety
    Vendor source accessed 2026-06-09
    • “If a prompt or document is detected as likely to generate inappropriate educational content, the shield blocks it and suggests alternative, safe inputs.”
  3. Microsoft Azure SOC 2 compliance offering
    Vendor source accessed 2026-06-13
    • “see the Azure SOC 2 Type 2 attestation report or Cloud services in audit scope”

Changelog

  1. Added to the catalog from the Azure AI Content Safety documentation.

Found an error? Corrections are welcome. Suggest an edit.