Skip to main content
BreachLens red-teams your AI agents and LLM endpoints the way an attacker would probe them: prompt injection, jailbreaks, system-prompt leakage, PII exfiltration, content-filter bypass, and excessive agent permissions. You give it an endpoint to attack; it runs a battery of adversarial skills and judges the responses.

​
Register an agent

Open AI Agents → Add agent and describe the endpoint under test:
  • Name
  • Agent type — the kind of endpoint (OpenAI-compatible, Azure AI Foundry, Anthropic API, Ollama, or a custom HTTP endpoint)
  • Endpoint — the URL prompts are POSTed to
  • Auth — how to authenticate to that endpoint (the header each kind sends is in Auth kinds below)
  • Optionally a Model ID (the deployment/model name) and a System-prompt hint to sharpen the probes.
The auth value is encrypted at rest and never returned.

​
Auth kinds

Use Test connection before scanning — it confirms BreachLens can reach and authenticate to the endpoint (it auto-detects chat-completions vs the newer responses API).

​
You need a judge

The red-team skills probe your agent; a judge model decides whether each response is a real finding. The judge is one of your configured AI providers — Anthropic, OpenAI, or a local Ollama. If no AI provider is active for your org, the scan can’t judge results and will fail, so configure one first.
The judge and the target are independent: you can red-team an Azure-hosted agent while judging with a local Ollama model, keeping evaluation fully in-house.

​
Run a scan

1

Open the agent

Go to AI Agents and click the registered agent.
2

Run the scan

Click Run scan. BreachLens runs its adversarial skills — prompt-injection, system-prompt-leak, jailbreak, PII-exfil, content-filter-validation, and permissions-audit — against the endpoint.
3

Review findings

Each confirmed weakness is a finding with the prompt that triggered it and the judge’s reasoning.

​
Next steps

Scan an MCP server

Security-test the Model Context Protocol servers your agents connect to.

Identities & NHI

The non-human identities and keys your agents hold — over-permissioned or stale.