Skip to main content
AI RUNTIME SECURITY SCANNER

Test Your Live AI
Before Attackers Do

Real attack simulations against your production AI endpoints

22+ attack categories, 500+ templates covering prompt injection, jailbreak, PII leakage, RAG poisoning, agent attacks, and more. Audit-grade evidence for compliance teams.

No instrumentation requiredLocalhost works instantlyAudit-grade evidence
22+
Attack Categories
500+
Attack Templates
9
Compliance Frameworks
Real-time
Live Results
⚠️ The Gap in AI Security Testing

Static Scans Miss Runtime Attacks

Code analysis tells you what could go wrong. Runtime testing tells you what actually gets through your defenses today.

Traditional Pen Testing

  • Quarterly or annual — not continuous
  • Manual, expensive, slow to deliver results
  • No coverage for AI-specific attacks
  • Results stale by next deployment

HAIEC Runtime Security Scanner

  • On-demand and continuous — test any time
  • Automated, results in minutes, not weeks
  • 22+ AI-native attack categories, 500+ templates
  • Run after every deploy to stay current

What We Test

22+ attack categories, 500+ templates drawn from OWASP LLM Top 10, real-world incidents, and original HAIEC research

Prompt Injection

Critical

Direct and indirect prompt injection attacks that override system instructions or inject malicious commands

Templates:40+ templates
Maps to:OWASP LLM01, CWE-77, SOC 2 CC7.2

Jailbreak

Critical

Attempts to bypass safety guardrails and make the AI generate restricted or harmful content

Templates:50+ templates
Maps to:OWASP LLM01, ISO 42001 A.6.1

Role Confusion

High

Manipulating the AI into assuming unauthorized roles (DAN, developer mode, etc.)

Templates:30+ templates
Maps to:OWASP LLM01, ISO 42001 A.6.1

Context Injection

High

Injecting false facts, policies, or instructions into the conversation context

Templates:25+ templates
Maps to:OWASP LLM02, CWE-20

Extraction / System Prompt Leak

High

Extracting confidential system prompts, internal instructions, or proprietary knowledge

Templates:35+ templates
Maps to:OWASP LLM07, CWE-200, GDPR Art 32

Tool Forcing

Critical

Forcing unauthorized tool or function calls, code execution, or privileged operations

Templates:20+ templates
Maps to:OWASP LLM07, CWE-94, SOC 2 CC6.1

PII Leakage

Critical

Making the AI reveal personally identifiable information, training data, or user records

Templates:30+ templates
Maps to:GDPR Art 32, HIPAA 164.312(b), CWE-200

Toxicity

High

Provoking the AI to generate offensive, hateful, or harmful content via adversarial prompting

Templates:25+ templates
Maps to:EU AI Act Art 9, ISO 42001 A.6.2

Bias Exploitation

High

Exploiting AI biases to generate discriminatory outputs or unfair decisions

Templates:20+ templates
Maps to:EU AI Act Art 10, NYC LL144, ISO 42001 A.6.5

DoS / Context Overflow

Medium

Extremely long inputs designed to cause context overflow, latency spikes, or denial of service

Templates:15+ templates
Maps to:CWE-770, SOC 2 CC7.2

Multimodal Attacks

High

Cross-modal injection via images, audio, or documents that embed attack payloads

Templates:20+ templates
Maps to:OWASP LLM01, CWE-20

Data Exfiltration

Critical

Indirect data exfiltration via markdown links, webhooks, or encoded outputs

Templates:25+ templates
Maps to:GDPR Art 32, CWE-200, SOC 2 CC6.6

RAG Poisoning

Critical

Exploiting retrieval-augmented generation pipelines via poisoned documents or metadata injection

Templates:20+ templates
Maps to:OWASP LLM03, CWE-20, SOC 2 CC6.1

Agent Attacks

Critical

Multi-step manipulation of AI agents to chain unauthorized tool calls or escalate privileges

Templates:30+ templates
Maps to:OWASP LLM08/09, ISO 42001 A.6.1

Goal Hijacking

High

Redirecting the AI's primary objective to serve attacker goals or abandon its intended task

Templates:25+ templates
Maps to:OWASP LLM09, ISO 42001 A.6.1

Encoding Bypass

High

Using Base64, Unicode, ROT13, or other encodings to bypass content safety filters

Templates:20+ templates
Maps to:CWE-20, OWASP LLM01

Cost Explosion

Medium

Crafted inputs designed to maximize token usage and inflate API costs unsustainably

Templates:10+ templates
Maps to:CWE-770, SOC 2 CC7.2

Chatbot Manipulation

Medium

Gradual multi-turn manipulation that shifts chatbot behavior across a conversation session

Templates:20+ templates
Maps to:ISO 42001 A.6.2

Conversation Hijacking

High

Injecting content that seizes control of another user's conversation or cross-contaminates sessions

Templates:15+ templates
Maps to:CWE-284, SOC 2 CC6.1

Brand Safety

Medium

Coercing the AI to generate off-brand, controversial, or reputationally damaging content

Templates:15+ templates
Maps to:ISO 42001 A.6.2

Hallucination Exploit

Medium

Exploiting AI hallucinations to generate false but authoritative-sounding misinformation

Templates:15+ templates
Maps to:EU AI Act Art 13, ISO 42001 A.6.5

Compliance Bypass

Critical

Tricking the AI into violating regulatory requirements or legal constraints it should enforce

Templates:20+ templates
Maps to:GDPR, HIPAA, EU AI Act Art 9, SOC 2 CC6.1

Social Engineering

High

Psychological manipulation (urgency, authority, sympathy) to bypass AI safety measures

Templates:30+ templates
Maps to:ISO 42001 A.6.1, CWE-20

How It Works

From endpoint registration to audit-grade report in five steps

01

Register Your Endpoint

Provide your AI endpoint URL and authentication details. Localhost works immediately — no verification needed. Production endpoints require domain verification (DNS TXT, meta-tag, or file-based).

Supports REST APIs, OpenAI-compatible chat/completions format, LangChain, and custom protocols.

02

Select Attack Profile

Choose from 22+ attack categories and 500+ templates. Optionally configure a scan profile (VOICE, AGENTIC, EMBEDDED_SAAS, RAG, AI_ASSISTED_DEV) to run profile-appropriate attack variants.

Templates are sourced from OWASP LLM Top 10, real-world incident reports, and original HAIEC research.

03

Live Attack Simulation

Our Modal-powered engine sends safe, non-destructive attack payloads to your endpoint in real time. Every request and response is captured and timestamped as cryptographic evidence.

Tests run in isolated execution contexts. No attack payload ever touches your database or filesystem.

04

AI-Graded Results

Each response is evaluated by a safety scorer to detect whether the attack succeeded. Findings are classified by severity (CRITICAL, HIGH, MEDIUM, LOW) and attack category.

Safety scoring uses multi-signal detection: pattern matching, semantic analysis, and structural violation checks.

05

Audit-Grade Report

Get an executive report with risk score, findings breakdown, prioritized recommendations, and an integrity hash proving the report has not been altered since generation.

Export as PDF, HTML, or JSON. Reports include compliance mapping appendix for auditor submission.

Any AI Endpoint, Any Stack

If it accepts HTTP POST with a user message and returns AI output, we can test it

AI Chatbots

Customer-facing chat windows, support bots, onboarding assistants

OpenAI / Anthropic Wrappers

Any API route that proxies or wraps GPT, Claude, Gemini, or other LLMs

RAG Applications

LangChain, LlamaIndex, vector-store-backed Q&A systems

AI Agents

Autonomous agents with tool access, code execution, or external API calls

Attack Flow Architecture

HAIEC Platform
Attack orchestration
Modal Engine
Isolated execution
Your AI Endpoint
Live production system
Safety Scorer
Response analysis
Audit Report
Evidence + recommendations

Every request/response pair is captured as timestamped evidence. Report integrity is verified with SHA-256 hash.

Why HAIEC Runtime Security

Purpose-built for AI systems — not a generic pen testing tool

Minutes to First Test

Point at any HTTP AI endpoint. No instrumentation, no SDK changes, no code deployment.

Compliance Evidence

Audit-grade reports with integrity hash, test evidence, and mappings to OWASP, SOC 2, GDPR, HIPAA, EU AI Act.

Continuous Monitoring

Schedule recurring tests and get alerted when new vulnerabilities are detected between deployments.

CI/CD Ready

Trigger tests from your pipeline. Block deploys if critical vulnerabilities are found.

Compliance-Ready Evidence

Every test generates findings mapped to applicable regulatory frameworks

OWASP LLM Top 10
SOC 2 Type II
ISO 27001
ISO 42001
GDPR Art 32
HIPAA 164.312
EU AI Act
NIST AI RMF
NYC LL144

Test Your AI Endpoint Now

No credit card. No instrumentation. Results in minutes.