AI Vulnerability Scan
Test your AI agent for safety and security vulnerabilities with automated red teaming attacks.
The vulnerability scan helps you identify weaknesses in your AI agent by testing it against common attack patterns. This includes:
Prompt injection attempts
Harmful content generation
Data extraction attacks
Other OWASP GenAI Top 10 risks
How it works: The scan runs dozens of specialized red teaming probes that adapt to your agent’s capabilities and use case. Each probe tests for specific vulnerabilities and provides detailed results.
What you get: * A security grade (A-D) based on detected vulnerabilities * Detailed breakdown by attack category and severity * Conversation logs showing exactly how attacks were performed * Actionable insights to improve your agent’s defenses
Quick start
Go to Scan in the left sidebar
Click Launch Scan
Select your agent and vulnerability categories to test
Click Launch Scan to start the red teaming process
Review results and take action on detected vulnerabilities
Vulnerability categories
The scan tests for these common AI security risks:
Security Risks
Malicious prompts that bypass your agent’s safety instructions
Attempts to expose sensitive data from your model’s training
Leakage of system configurations or internal data
Unauthorized access to user data or privacy violations
Safety Risks
Toxic, offensive, or policy-violating content creation
Actions beyond intended scope or authority level
Resource exhaustion attacks that disable your system
Business Risks
False or misleading information that damages trust
Outputs that harm your brand or public perception
Content leading to legal liability or financial harm
Advice outside your agent’s intended expertise