Send a request

Microsoft Prompt Shields (Azure AI Content Safety)

by Microsoft

Detect prompt attacks hidden in documents

Cloud service that detects direct and document-hidden prompt attacks before the model acts on them.

PaidLimited checks · 3 checksSome practice neededBrowser
Visit website

You go to the maker’s website. OROBO earns nothing from it.

Have it set up for you instead:Request setup by OROBOOr start with the AI Compass: a written assessment at a fixed price of €490 (businesses only).

How it runs for you

Simulation starting …

Illustration, not a real test run

What you get

What you get

  1. 01Detects direct jailbreak attempts
  2. 02Finds instructions hidden inside documents
  3. 03Checks before your model responds

For you if …

  • Developers on Azure OpenAI or Microsoft Foundry
  • Apps that process third-party documents

Pick something else if …

  • Filtering harmful content; it does not cover that
  • Non-English text, where it is more limited

How to start

In three steps.

What you need
  • An Azure account
  • Your own AI app with API access
  1. 1Create an Azure AI Content Safety resource
  2. 2Send the prompt and documents to the Prompt Shields API
  3. 3Stop the request when an attack is flagged

Safety check

Limited checks · 3 checks

3 of 3 possible checks passed. Fewer than four automated checks are possible here, so we show no trust score.

Limited checks · 3 checks
Is it maintained?
  • Website reachable
  • Prices on the maker’s site
Technical details & what we don’t check
  • Website loads fast
  • Website protection settings: 5 of 6 (website only, not the software)HSTS, CSP, nosniff, Frame-Schutz, Referrer-Policy

Claims about protection come from the maker. The trust score checks public signals, not effectiveness.

We automatically check origin, code patterns, licence, maintenance and reachability — again every day. We do not check whether the software fits your purpose, how it handles your data, or whether it works without errors. Last checked 3 hours ago. How OROBO checks

Alternatives for the same goal

garakMake it safe · NVIDIAHave your language model attacked on purposeOpen SourceTrust high, 100For developersGuardrails AIMake it safe · Guardrails AI (Harvey)Check AI answers before they move onOpen SourceTrust high, 100For developersNeMo GuardrailsMake it safe · NVIDIAFirm guardrails for your chatbotOpen SourceTrust high, 100For developersGiskardMake it safe · GiskardScan LLM apps for hallucinations and leaksOpen SourceTrust high, 100For developersPyRITMake it safe · Microsoft (AI Red Team)Automate red teaming for generative AIOpen SourceTrust high, 100For developersMeta PurpleLlama (Llama Guard 4, Prompt Guard 2, LlamaFirewall)Make it safe · MetaFree guard models for your own AIOpen SourceTrust high, 100Runs offlineSnyk Agent Scan (formerly Invariant MCP-Scan)Make it safe · Snyk (ex-Invariant Labs team)Scan installed MCP servers and skills for trapsOpen SourceTrust high, 100For developersCisco Skill ScannerMake it safe · Cisco AI DefenseCheck agent skills before you install themOpen SourceTrust high, 100For developers

Facts

AreaMake it safe
PricePaid
Runs onBrowser
I am the maker