Skip to content
azure-ai-contentsafety-py logo

Azure AI Content Safety SDK for Python

azure-ai-contentsafety-py

Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.

SKILL.md

Full skill instructions

Azure AI Content Safety SDK for Python

Detect harmful user-generated and AI-generated content in applications.

Installation

pip install azure-ai-contentsafety

Environment Variables

CONTENT_SAFETY_ENDPOINT=https://<resource>.cognitiveservices.azure.com
CONTENT_SAFETY_KEY=<your-api-key>

Authentication

API Key

from azure.ai.contentsafety import ContentSafetyClient
from azure.core.credentials import AzureKeyCredential
import os

client = ContentSafetyClient(
    endpoint=os.environ["CONTENT_SAFETY_ENDPOINT"],
    credential=AzureKeyCredential(os.environ["CONTENT_SAFETY_KEY"])
)

Entra ID

from azure.ai.contentsafety import ContentSafetyClient
from azure.identity import DefaultAzureCredential

client = ContentSafetyClient(
    endpoint=os.environ["CONTENT_SAFETY_ENDPOINT"],
    credential=DefaultAzureCredential()
)

Analyze Text

from azure.ai.contentsafety import ContentSafetyClient
from azure.ai.contentsafety.models import AnalyzeTextOptions, TextCategory
from azure.core.credentials import AzureKeyCredential

client = ContentSafetyClient(endpoint, AzureKeyCredential(key))

request = AnalyzeTextOptions(text="Your text content to analyze")
response = client.analyze_text(request)

# Check each category
for category in [TextCategory.HATE, TextCategory.SELF_HARM, 
                 TextCategory.SEXUAL, TextCategory.VIOLENCE]:
    result = next((r for r in response.categories_analysis 
                   if r.category == category), None)
    if result:
        print(f"{category}: severity {result.severity}")

Analyze Image

from azure.ai.contentsafety import ContentSafetyClient
from azure.ai.contentsafety.models import AnalyzeImageOptions, ImageData
from azure.core.credentials import AzureKeyCredential
import base64

client = ContentSafetyClient(endpoint, AzureKeyCredential(key))

# From file
with open("image.jpg", "rb") as f:
    image_data = base64.b64encode(f.read()).decode("utf-8")

request = AnalyzeImageOptions(
    image=ImageData(content=image_data)
)

response = client.analyze_image(request)

for result in response.categories_analysis:
    print(f"{result.category}: severity {result.severity}")

Image from URL

from azure.ai.contentsafety.models import AnalyzeImageOptions, ImageData

request = AnalyzeImageOptions(
    image=ImageData(blob_url="https://example.com/​image.jpg")
)

response = client.analyze_image(request)

Text Blocklist Management

Create Blocklist

from azure.ai.contentsafety import BlocklistClient
from azure.ai.contentsafety.models import TextBlocklist
from azure.core.credentials import AzureKeyCredential

blocklist_client = BlocklistClient(endpoint, AzureKeyCredential(key))

blocklist = TextBlocklist(
    blocklist_name="my-blocklist",
    description="Custom terms to block"
)

result = blocklist_client.create_or_update_text_blocklist(
    blocklist_name="my-blocklist",
    options=blocklist
)

Add Block Items

from azure.ai.contentsafety.models import AddOrUpdateTextBlocklistItemsOptions, TextBlocklistItem

items = AddOrUpdateTextBlocklistItemsOptions(
    blocklist_items=[
        TextBlocklistItem(text="blocked-term-1"),
        TextBlocklistItem(text="blocked-term-2")
    ]
)

result = blocklist_client.add_or_update_blocklist_items(
    blocklist_name="my-blocklist",
    options=items
)

Analyze with Blocklist

from azure.ai.contentsafety.models import AnalyzeTextOptions

request = AnalyzeTextOptions(
    text="Text containing blocked-term-1",
    blocklist_names=["my-blocklist"],
    halt_on_blocklist_hit=True
)

response = client.analyze_text(request)

if response.blocklists_match:
    for match in response.blocklists_match:
        print(f"Blocked: {match.blocklist_item_text}")

Severity Levels

Text analysis returns 4 severity levels (0, 2, 4, 6) by default. For 8 levels (0-7):

from azure.ai.contentsafety.models import AnalyzeTextOptions, AnalyzeTextOutputType

request = AnalyzeTextOptions(
    text="Your text",
    output_type=AnalyzeTextOutputType.EIGHT_SEVERITY_LEVELS
)

Harm Categories

CategoryDescription
HateAttacks based on identity (race, religion, gender, etc.)
SexualSexual content, relationships, anatomy
ViolencePhysical harm, weapons, injury
SelfHarmSelf-injury, suicide, eating disorders

Severity Scale

LevelText RangeImage RangeMeaning
0SafeSafeNo harmful content
2LowLowMild references
4MediumMediumModerate content
6HighHighSevere content

Client Types

ClientPurpose
ContentSafetyClientAnalyze text and images
BlocklistClientManage custom blocklists

Best Practices

  1. Use blocklists for domain-specific terms
  2. Set severity thresholds appropriate for your use case
  3. Handle multiple categories — content can be harmful in multiple ways
  4. Use halt_on_blocklist_hit for immediate rejection
  5. Log analysis results for audit and improvement
  6. Consider 8-severity mode for finer-grained control
  7. Pre-moderate AI outputs before showing to users

When to Use

This skill is applicable to execute the workflow or actions described in the overview.

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

More skills from boisenoise

database-cloud-optimization-cost-optimize logo
boisenoise/skills-collections

database-cloud-optimization-cost-optimize

You are a cloud cost optimization expert specializing in reducing infrastructure expenses while maintaining performance and reliability. Analyze cloud spending, identify savings opportunities, and implement cost-effective architectures across AWS, Azure, and GCP.

10 0
View
postmark-automation logo
boisenoise/skills-collections

postmark-automation

Automate Postmark email delivery tasks via Rube MCP (Composio): send templated emails, manage templates, monitor delivery stats and bounces. Always search tools first for current schemas.

10 0
View
game-development logo
boisenoise/skills-collections

game-development

Game development orchestrator. Routes to platform-specific skills based on project needs.

10 0
View
test-fixing logo
boisenoise/skills-collections

test-fixing

Systematically identify and fix all failing tests using smart grouping strategies. Use when explicitly asks to fix tests (\"fix these tests\", \"make tests pass\"), reports test failures (\"tests are failing\", \"test suite is broken\"), or completes implementation and wants tests passing.

10 0
View
notebooklm logo
boisenoise/skills-collections

notebooklm

Interact with Google NotebookLM to query documentation with Gemini's source-grounded answers. Each question opens a fresh browser session, retrieves the answer exclusively from your uploaded documents, and closes.

10 0
View
agent-evaluation logo
boisenoise/skills-collections

agent-evaluation

Testing and benchmarking LLM agents including behavioral testing,

10 0
View
clickup-automation logo
boisenoise/skills-collections

clickup-automation

Automate ClickUp project management including tasks, spaces, folders, lists, comments, and team operations via Rube MCP (Composio). Always search tools first for current schemas.

10 0
View
wordpress-penetration-testing logo
boisenoise/skills-collections

wordpress-penetration-testing

Assess WordPress installations for common vulnerabilities and WordPress 7.0 attack surfaces.

10 0
View
ln-761-secret-scanner logo
boisenoise/skills-collections

ln-761-secret-scanner

Scans codebase for hardcoded secrets with severity classification and remediation guidance. Use when auditing a project for leaked credentials.

10 0
View
azure-monitor-ingestion-java logo
boisenoise/skills-collections

azure-monitor-ingestion-java

Azure Monitor Ingestion SDK for Java. Send custom logs to Azure Monitor via Data Collection Rules (DCR) and Data Collection Endpoints (DCE).

10 0
View
ln-513-agent-reviewer logo
boisenoise/skills-collections

ln-513-agent-reviewer

Runs parallel external agent reviews (Codex + Gemini) on code changes. Process-as-arrive, critical verification with debate. Returns filtered suggestions.

10 0
View
drip-jobs-automation logo
boisenoise/skills-collections

drip-jobs-automation

Automate Drip Jobs tasks via Rube MCP (Composio). Always search tools first for current schemas.

10 0
View

Popular AI tools

Kaiber logo
Video

Kaiber

Generate, edit, and beat-sync AI video with leading models in one workspace.

Paid
View
Vimcal logo
Productivity

Vimcal

The world's fastest calendar for remote work

Free
View

Transform Your Design with AI Designer by ImgCreator.ai

Freemium
View
Akool AI logo
Content & writing

Akool AI

Revolutionizing Video Production with AI-Powered Creativity

Paid
View

Extend an image past the frame and let AI fill the new aspect ratio.

Freemium
View
StarByFace logo
Security

StarByFace

Discover your celebrity doppelgänger with StarByFace!

Free
View
C

ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.

Freemium
View
Opus Clip logo
Coding & apps

Opus Clip

Opus.ai: Revolutionize Your Web Experience

Free
View