---
title: "Azure AI Content Safety SDK for Java: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/skills/microsoft-azure-ai-contentsafety-java/
description: "Microsoft's Java guide to com.azure:azure-ai-contentsafety at 1.1.0-beta.1: text and image harm analysis with ContentSafetyClient, and blocklist management with BlocklistClient."
---

# Azure AI Content Safety SDK for Java: review, setup & limitations · Undominated.ai

> Microsoft's Java guide to com.azure:azure-ai-contentsafety at 1.1.0-beta.1: text and image harm analysis with ContentSafetyClient, and blocklist management with BlocklistClient.

[← Explore all skills](/skills/)

CONTENT MODERATION / Microsoft

# Azure AI Content Safety SDK for Java

Microsoft's Java guide to com.azure:azure-ai-contentsafety at 1.1.0-beta.1: text and image harm analysis with ContentSafetyClient, and blocklist management with BlocklistClient.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/microsoft/skills/tree/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-java/skills/azure-ai-contentsafety-java)

SOURCE REVIEW

 Reviewed 2026-10-21
 Evidence 6 linked sources
 Publisher Microsoft
 Licence [MIT ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/LICENSE)
 Revision fc164ba1d7a0
 [Read what was—and wasn’t—checked ↓](#review)

“Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text/image analysis, blocklist management, or harm detection for hate, violence, sexual content, and self-harm.”

 [Microsoft · upstream description ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-java/skills/azure-ai-contentsafety-java/SKILL.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - It pairs ContentSafetyClient for analysis with BlocklistClient for blocklist create or update, list, get, item add, item list, item remove and delete.
- It states the severity scales (text 0-7 with default outputs 0, 2, 4, 6; images 0, 2, 4, 6) and shows category selection with EIGHT_SEVERITY_LEVELS output.
- Its practice list says blocklist changes take ~5 minutes to take effect and that strict moderation typically blocks severity >= 4.

### A good fit for

 - Score Java service text for hate and violence only, at eight severity levels
- Analyze text against a named blocklist with setHaltOnBlocklistHit(true) and report the matched items
- Moderate an image read from disk, or one at a URL, from a Java application
- Add, list and remove the terms in a Content Safety text blocklist

### Weigh up before choosing

 - Both install lines Microsoft prints for this skill, `npx skills add microsoft/skills --skill azure-sdk-java` and `/plugin install azure-sdk-java@skills`, install the whole azure-sdk-java plugin rather than the Content Safety skill alone.
- The Installation block pins com.azure:azure-ai-contentsafety to 1.1.0-beta.1, a beta version.
- The environment block says CONTENT_SAFETY_KEY is "Only required for AzureKeyCredential auth", but the key sample builds both clients with com.azure.core.credential.KeyCredential.
- The DefaultAzureCredential sample builds only a ContentSafetyClient; every blocklist sample uses the key-authenticated BlocklistClient.
- Blocklist item removal and blocklist deletion run with no confirmation step.
- azure-ai-contentsafety-java/references/examples.md sits beside SKILL.md, which does not link to it; this review did not open it.
- The azure-ai-contentsafety-java directory was last changed at the pin by commit e7ee58fc, committed 2026-04-29.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - .github/plugins/azure-sdk-java/skills/azure-ai-contentsafety-java/SKILL.md (all 297 lines)
- .github/plugins/azure-sdk-java/README.md
- .github/plugins/azure-sdk-java/.claude-plugin/plugin.json
- README.md
- LICENSE

### Our findings

 - The harm categories are Hate, Sexual, Violence and Self-harm.
- The DefaultAzureCredential sample calls requireEnvVars(AzureIdentityEnvVars.AZURE_TOKEN_CREDENTIALS) and leaves ManagedIdentityCredentialBuilder as a commented production alternative.
- Error handling catches HttpResponseException and names InvalidRequestBody, ResourceNotFound and TooManyRequests as common codes.
- Practice 2 says to request only the categories needed to reduce latency; practice 4 says to process items in parallel for throughput.
- The frontmatter declares license MIT, author Microsoft, version 1.0.0 and package com.azure:azure-ai-contentsafety. It declares no allowed-tools.

### Not established by this review

 - No text or image was analysed, and no blocklist or blocklist item was created, changed or removed.
- No Maven dependency on com.azure:azure-ai-contentsafety was added to a project.
- Neither the azure-sdk-java plugin nor azure-ai-contentsafety-java was installed, and references/examples.md was not read.
- Not executed: it was not installed or run.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Add a skill to your workflow.

[Upstream setup instructions ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-java/README.md)
 - The azure-sdk-java plugin README prints `npx skills add microsoft/skills --skill azure-sdk-java` under Install. It installs the whole azure-sdk-java plugin, whose skill table lists azure-ai-contentsafety-java; it does not install that skill alone.
- The same README prints `/plugin install azure-sdk-java@skills`, which also brings in azure-ai-contentsafety-java together with every other skill in the plugin. The repository README runs plugin commands inside Copilot CLI after `/plugin marketplace add microsoft/skills`.

### Before you start

 - The skill gives a Maven <dependency> on com.azure:azure-ai-contentsafety version 1.1.0-beta.1, not an install command. This review added nothing.
- CONTENT_SAFETY_ENDPOINT, plus CONTENT_SAFETY_KEY for the key samples, or AZURE_TOKEN_CREDENTIALS when DefaultAzureCredential is used in production.
- Copilot CLI, where `/plugin install azure-sdk-java@skills` adds this Content Safety skill with the rest of the plugin.

### Compatibility

Copilot CLI · GitHub Copilot in VS Code

### Implementation

Java

### Reference text; text, images and blocklist changes reach Content Safety only from Java code an operator runs

 - The azure-ai-contentsafety-java frontmatter declares no allowed-tools; its directory holds SKILL.md and references/examples.md, and no scripts.
- Samples send text, the bytes of a local image.png, or an image URL (https://example.com/image.jpg) to the endpoint in CONTENT_SAFETY_ENDPOINT.
- Blocklist samples create or update, fill, list, prune and delete my-blocklist on that resource.
- They authenticate with CONTENT_SAFETY_KEY through KeyCredential, or with DefaultAzureCredential.

### Cost model

Free to copy under MIT. The file states no price for Content Safety analysis or blocklist calls made from Java, and this review looked none up.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [azure-ai-contentsafety-java SKILL.md at the pin ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-java/skills/azure-ai-contentsafety-java/SKILL.md) Checked 2026-10-21 https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-java/skills/azure-ai-contentsafety-java/SKILL.md Supports: name, upstreamDescription, summary, whySelected, bestFor, limitations, review.findings, install.prerequisites, access.permissions
- [azure-sdk-java plugin README ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-java/README.md) Checked 2026-10-21 https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-java/README.md Supports: install.sourceUrl, install.steps, limitations (install scope)
- [azure-sdk-java plugin.json ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-java/.claude-plugin/plugin.json) Checked 2026-10-21 https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-java/.claude-plugin/plugin.json Supports: publisher, license (plugin licence field)
- [Repository README ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/README.md) Checked 2026-10-21 https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/README.md Supports: compatibility, install.steps (Copilot CLI plugin commands)
- [Repository LICENSE ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/LICENSE) Checked 2026-10-21 https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/LICENSE Supports: license
- [Commit e7ee58fc, the last change to azure-ai-contentsafety-java at the pin ↗](https://github.com/microsoft/skills/commit/e7ee58fc1fa669841e06f8d27359e0533d148394) Checked 2026-10-21 https://github.com/microsoft/skills/commit/e7ee58fc1fa669841e06f8d27359e0533d148394 Supports: limitations (last commit date)

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Azure AI Content Safety REST SDK for TypeScript ↗ Microsoft's TypeScript guide to the @azure-rest/ai-content-safety REST client: scoring text and images for hate, sexual, violence and self-harm severity, managing custom blocklists, and folding the results into one allow-or-block decision.](/skills/microsoft-azure-ai-contentsafety-ts/)[### Azure AI Content Safety for Python ↗ Pins Microsoft's Python Content Safety skill, which keeps new code on Entra credentials and can stop analysis when a blocklist matches.](/skills/microsoft-azure-ai-contentsafety-py/)[### AKS Automatic Readiness ↗ Pins Microsoft's AKS Automatic readiness skill, which assesses a cluster or local manifests without changing the cluster and writes files only after an accepted diff.](/skills/microsoft-azure-kubernetes-automatic-readiness/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Choose a toolkit](/tools/)
- [Inspect execution hosts](/agents/)
- [Check tool access](/mcp-servers/)
- [Check project dependencies](/check-repo/)
