azure-ai-content-safety

azure-ai-content-safety is a skill for Claude Code, Codex from vinayaklatthe/microsoft-security-skills. It costs 221 tokens per session (2,046 once invoked), scanned A, original, MIT.

Guidance for adding Azure AI Content Safety checks to applications that process text, images, or generative-AI interactions.

In plain words
What is it for?
Plan moderation and guardrails for chat assistants, agents, retrieval-based applications, and multimodal products, including severity-based checks for harmful categories.
Why use it?
It helps detect harmful content, prompt-injection attempts, jailbreaks, and unsupported answers before they cause problems. It can cover both user inputs and application outputs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Plan moderation and guardrails for chat assistants, agents, retrieval-based applications, and multimodal products, including severity-based checks for harmful categories.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vinayaklatthe/microsoft-security-skills/azure-ai-content-safety
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add vinayaklatthe/microsoft-security-skills --skill azure-ai-content-safety
Clone the repo
git clone --depth 1 https://github.com/vinayaklatthe/microsoft-security-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for azure-ai-content-safety

README.md
[![agentmods](https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/azure-ai-content-safety/github.svg)](https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/azure-ai-content-safety)
Your own site
<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/azure-ai-content-safety"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/azure-ai-content-safety/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for azure-ai-content-safety

Your own site · 80×15
<a href="https://agentmods.dev/skills/vinayaklatthe/microsoft-security-skills/azure-ai-content-safety"><img src="https://agentmods.dev/badge/skills/vinayaklatthe/microsoft-security-skills/azure-ai-content-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 221 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,046 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00221 $0.02046
Opus 5 $0.00111 $0.01023
Sonnet 5 $0.00044 $0.00409
Haiku 4.5 $0.00022 $0.00205

Measured 13d ago against content hash 33473445ae0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

azure-ai-content-safety scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/azure-ai-content-safety/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Azure AI Content Safety

Azure AI Content Safety is the platform for real-time content moderation and generative AI safety. It analyzes text, images, and multimodal content for harm categories, blocks prompt-injection / jailbreak attempts (Prompt Shields), detects ungrounded responses (Groundedness), and flags protected text/code reproduction.

It pairs with Azure OpenAI as built-in content filters (default safety net) and as configurable guardrails for any AI/LLM application (including non-Microsoft models).

When to use

Building or hardening any generative AI application — chat assistant, agent, RAG app, multimodal product — that needs guardrails on inputs and outputs.

Do not use this skill for SOC threat detection on AI workloads (defender-for-cloud-ai), end-user AI usage governance (purview-ai-hub), or generic AI application architecture.

Capability map

Capability What it does Where to apply
Text moderation Classifies text into hate, violence, sexual, self-harm (severity 0–7) Input + output
Image moderation Same categories on images User uploads, generated images
Multimodal moderation Text+image combined context Multimodal chat
Prompt Shields — User Prompt Detects jailbreak attempts in the user prompt Input
Prompt Shields — Indirect Detects injection in untrusted grounding content (RAG, tool results, web pages) Pre-grounding step
Groundedness detection Checks LLM response against grounding sources for hallucination Output
Protected material — text Detects verbatim copyrighted text Output
Protected material — code Detects reproduction of public-repo code Code-generation output
Custom categories Customer-defined harm categories (e.g., off-brand topics) Input + output
Blocklists Exact-match + regex blocklists Input + output

Approach

  1. Start with default Azure OpenAI content filters. Every Azure OpenAI deployment has a default Content Safety filter at medium severity across all four harm categories. Don't deploy without it.

Read the full file on GitHub · 143 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 13d ago First seen · 143 lines · 221 tokens per session scan A 33473445ae0b

Subscribe to this mod's changes

azure-ai-content-safety is a skill published in the GitHub repository vinayaklatthe/microsoft-security-skills (173 stars, last pushed 2mo ago), licensed MIT. It adds 221 tokens to every session and 2,046 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

deepspeed

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention.

davila7/claude-code-templates · 38 tokens

skill-meta-prompt

Craft better prompts using proven optimization techniques — use when your prompt needs refinement.

nyldn/claude-octopus · 19 tokens

dashscope

DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen3-asr-flash-filetrans). Use when generating images via Qwen-Image, narrating via Qwen-TTS, or transcribing with word-level timestamps via Qwen-ASR.

calesthio/OpenMontage · 93 tokens

session-rag-eval

Run and debug Chatbox session attachment RAG model evaluation with synthetic and real long-file fixtures.

chatboxai/chatbox · 25 tokens

microsoft-extensions-ai

Build provider-agnostic .NET AI integrations with Microsoft.Extensions.AI, IChatClient, embeddings, middleware, structured output, vector search, and evaluation. USE FOR: building or reviewing .NET code that uses Microsoft.Extensions.AI, Microsoft.Extensions.AI.Abstractions, IChatClient, IEmbeddingGenerator…

managedcode/dotnet-skills · 128 tokens

semantic-kernel

Build AI-enabled .NET applications with Semantic Kernel using services, plugins, prompts, and function-calling patterns that remain testable and maintainable. USE FOR: adding AI-driven prompts, plugins, or orchestration to a .NET app; reviewing kernel construction, service registration, or plugin usage; building…

managedcode/dotnet-skills · 116 tokens