Analysis · curated 3 Aug 2026

AI Security Vulnerabilities | Giskard Documentation

Coverage timeline

3 Aug 2026giskard.ai 19 Aug 2026giskard.ai

Why it matters

Prompt injection remains a foundational threat to deployed LLM systems, and reference material framing its subtypes and mitigations helps defenders understand the attack surface, though this entry is evergreen definitional content rather than a new finding.

The Giskard documentation glossary entry on prompt injection defines the vulnerability class where malicious inputs bypass content filters, override system instructions, or extract sensitive data, covering direct, indirect, and character injection subtypes. The page describes business impacts and points to Giskard's Hub UI and Python SDK for generating adversarial test cases and evaluation checks.