Overview

Comprehensive guide to AI security vulnerabilities and attack patterns tested by Giskard’s vulnerability scan.

The vulnerability scan uses specialized probes (structured adversarial tests) to stress-test AI systems and uncover weaknesses before malicious actors do. Each probe is designed to expose specific vulnerabilities in AI agents, from harmful content generation to unauthorized system access.

This catalog organizes vulnerabilities by risk category and provides detailed information about:

Attack patterns and techniques
Specific probes used for testing
Detection indicators
Mitigation strategies
Risk levels and business impact

Use this guide to understand the security landscape for AI systems and make informed decisions about which vulnerabilities to prioritize in your testing.

Vulnerability categories

Hallucination & Misinformation Tests for AI systems providing false, inconsistent, or fabricated information. Probes: 4

Harmful Content Generation Probes that attempt to bypass safety measures and generate dangerous, illegal, or harmful content across various categories. Probes: 17

Prompt Injection Attacks that attempt to manipulate AI agents through carefully crafted input prompts to override original instructions. Probes: 13

Excessive Agency Probes testing whether AI agents can be manipulated to perform actions beyond their intended scope or with inappropriate permissions. Probes: 6

Data Privacy Exfiltration Attacks aimed at extracting sensitive information, personal data, or confidential content from AI systems. Probes: 4

Internal Information Exposure Probes designed to extract system prompts, configuration details, or other internal information. Probes: 2

Training Data Extraction Attempts to extract or infer information from the AI model's training data. Probes: 1

Denial Of Service Probes that attempt to cause resource exhaustion or performance degradation. Probes: 2

Brand Damage & Reputation Tests for reputational risks and brand damage scenarios. Probes: 2

Legal & Financial Risk Probes targeting potential legal and financial liabilities. Probes: 1

Misguidance & Unauthorized Advice Probes that test whether AI agents can be manipulated to provide professional advice outside their intended scope. Probes: 2