BreakMesh – Vulnerability Simulator & Cyber Range

Scanner package

AI Security scanner

A consent-gated, harmless-canary assessment for websites that expose an LLM or AI chat interface.

What it checks

AI Security discovers AI-facing endpoints, then sends harmless canary text strings to check for prompt reflection, system-prompt exposure, prompt-injection indicators, response data leakage, training-data extraction indicators, model-extraction risk indicators, content-moderation bypass, and jailbreak pattern indicators.

It also evidences AI endpoint rate-limit readiness — whether the interface has any throttling in front of it at all.

Explicit consent required

This package requires confirming the target actually exposes an AI/LLM interface, and that no tool-calling or agentic actions are enabled on that endpoint — the probes are text-only canaries, never real exploit payloads, and are not safe to run against an endpoint that can take real-world actions.

All 10 checks in this package

Included from the Team plan and up.

  • AI Endpoint Discovery
  • AI Prompt Reflection Check
  • AI System Prompt Exposure
  • Prompt Injection Indicator
  • AI Response Data Leakage
  • AI Endpoint Rate-Limit Readiness
  • Training Data Extraction Indicator
  • Model Extraction Risk Indicator
  • Content Moderation Bypass Canary Probe
  • Jailbreak Pattern Indicator