Skills azure-ai-contentsafety-java
📦

azure-ai-contentsafety-java

Content revision r2 Safe ⚙️ External commands🌐 Network access🔑 Env variables

Build Java Content Moderation with Azure AI

Moderating text and images consistently requires careful SDK setup and policy handling. This skill provides Java patterns for Azure AI Content Safety analysis and blocklist management.

Supports: Claude Codex Code(CC)
🥉 78 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "azure-ai-contentsafety-java" from https://skillstore.io/skills/sickn33-azure-ai-contentsafety-java.md and its manifest at https://skillstore.io/api/skills/sickn33-azure-ai-contentsafety-java/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/sickn33-azure-ai-contentsafety-java.md Signed manifest GET /api/skills/sickn33-azure-ai-contentsafety-java/manifest Signed lockfile GET /api/skills/sickn33-azure-ai-contentsafety-java/lockfile

Test it

Using "azure-ai-contentsafety-java". Create a text moderation workflow that blocks severity 4 or higher.

Expected outcome:

  • Client setup uses environment-based Azure credentials.
  • The workflow analyzes selected harm categories.
  • Severity 4 or higher produces a block decision.
  • Lower severities follow the configured review policy.

Using "azure-ai-contentsafety-java". Add image moderation for uploaded files and public URLs.

Expected outcome:

The solution prepares image bytes or a public URL, submits the image for analysis, and maps category severities to review decisions.

Using "azure-ai-contentsafety-java". Create and populate a custom blocklist for prohibited terms.

Expected outcome:

The workflow creates or updates the named blocklist, adds described terms, checks returned item identifiers, and notes the propagation delay.

Security Audit

Safe
v5 • 7/23/2026 Open versioned report

All 37 static findings are false positives caused by Markdown fences, documentation placeholders, and standard environment-based Azure configuration. The skill contains Java and configuration examples; it does not execute shell commands or transmit credentials to unrelated services. No prompt injection, social engineering, or data-exfiltration intent was found.

1
Files scanned
293
Lines analyzed
0
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (33)
SKILL.md:15-21 SKILL.md:21-27 SKILL.md:27-46 SKILL.md:46-50 SKILL.md:50-57 SKILL.md:57-77 SKILL.md:77-88 SKILL.md:88-92 SKILL.md:92-100 SKILL.md:100-104 SKILL.md:104-119 SKILL.md:119-123 SKILL.md:123-142 SKILL.md:142-146 SKILL.md:146-152 SKILL.md:152-158 SKILL.md:158-175 SKILL.md:175-179 SKILL.md:179-197 SKILL.md:197-201 SKILL.md:201-209 SKILL.md:209-213 SKILL.md:213-216 SKILL.md:216-220 SKILL.md:220-229 SKILL.md:229-233 SKILL.md:233-239 SKILL.md:239-243 SKILL.md:243-245 SKILL.md:245-249 SKILL.md:249-259 SKILL.md:259-263 SKILL.md:263-266
🌐 Network access (2)
SKILL.md:148 SKILL.md:264
🔑 Env variables (2)
SKILL.md:34 SKILL.md:35
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/sickn33-azure-ai-contentsafety-java/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/sickn33-azure-ai-contentsafety-java/security.svg)](https://skillstore.io/skills/sickn33-azure-ai-contentsafety-java?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/sickn33-azure-ai-contentsafety-java?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-azure-ai-contentsafety-java/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/sickn33-azure-ai-contentsafety-java.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

sickn33. (2026). azure-ai-contentsafety-java security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-azure-ai-contentsafety-java/audits/5

BibTeX citation

@techreport{sickn33-sickn33-azure-ai-contentsafety-java-2026, author = {sickn33}, title = {azure-ai-contentsafety-java security audit report (audit version 5)}, institution = {Skillstore}, year = {2026}, number = {5}, url = {https://skillstore.io/skills/sickn33-azure-ai-contentsafety-java/audits/5}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "azure-ai-contentsafety-java security audit report (audit version 5)" version: "unspecified" type: report authors: - name: "sickn33" date-released: "2026-07-23" url: "https://skillstore.io/skills/sickn33-azure-ai-contentsafety-java/audits/5" identifiers: - type: other value: "skillstore:sickn33-azure-ai-contentsafety-java:audit:5" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
69
Community
83
Spec Compliance

What You Can Build

Add text moderation

Build category-based text checks with configurable severity levels and optional custom blocklists.

Review image uploads

Analyze uploaded image bytes or public image URLs before accepting user content.

Manage custom blocklists

Create, inspect, update, and remove organization-specific prohibited terms through the Java SDK.

Try These Prompts

Create Content Safety clients 
Show how to create Azure AI Content Safety Java clients using [API key or managed identity]. Include dependencies and required environment variables.
Analyze text by category 
Create a Java text analysis flow for [content source]. Check [categories] and explain how to apply a severity threshold of [level].
Moderate image submissions 
Design a Java image moderation flow for [file uploads or URLs]. Include response handling, category thresholds, and clear accept or review decisions.
Design a production moderation service 
Plan a Java moderation service for [application]. Include credentials, retries, blocklists, policy thresholds, privacy controls, telemetry, tests, and human review.

Best Practices

  • Keep endpoints and keys in environment-based configuration, and prefer DefaultAzureCredential where available.
  • Define category thresholds with policy stakeholders and test them against representative content.
  • Handle rate limits and service errors, and avoid logging raw moderated content or blocklist entries.

Avoid

  • Do not hardcode credentials or commit secrets to source control.
  • Do not apply one threshold to every category without policy validation.
  • Do not use an automated moderation result as the only review for high-impact decisions.

Frequently Asked Questions

What Azure service does this skill use?
It uses Azure AI Content Safety through the Java SDK.
Can it analyze both text and images?
Yes. The examples cover text input, image bytes, and public image URLs.
Which authentication methods are shown?
The skill shows an API key with KeyCredential and identity-based authentication with DefaultAzureCredential.
Does it support custom blocklists?
Yes. It covers creating, listing, updating, deleting, and populating text blocklists.
Does the skill define the correct moderation threshold?
No. Teams must select thresholds based on policy, risk, testing, and applicable requirements.
Is this a complete production implementation?
No. It provides focused SDK patterns and requires application integration, testing, monitoring, privacy controls, and deployment work.

Developer Details

Author

sickn33

License

MIT

Skillstore revision

r2

Version notice

The author did not declare a version.

Repository

https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/azure-ai-contentsafety-java

Ref

86d877f219e2131f05dd5b37c5e329c71c7b8ec4

Maintenance freshness

7/26/2026

Usage

5 downloads · 161 views

File structure

📄 SKILL.md