Shypd.aiThe largest open index of AI toolsGiskard is an AI security platform that provides continuous AI red teaming and LLM security. It helps detect vulnerabilities, improve LLM security, and safeguard AI systems for enterprises.
Trending
About
Giskard is an AI security platform designed to help enterprises deploy GenAI agents safely by providing continuous AI red teaming and LLM security. It features a red teaming engine that automatically generates sophisticated attack scenarios to detect vulnerabilities in AI agents before they reach production. The platform offers comprehensive test coverage for both security and quality issues, including prompt injection, data disclosure, sycophancy attacks, hallucinations, and inappropriate denials. Giskard supports various LLM agents and operates as a black-box testing tool, accessible via an API endpoint. It also provides features for data residency, granular access controls, and compliance with GDPR, SOC 2 Type II, and HIPAA.
Capabilities
Pricing & Plans
Freemium · Enterprise · Open Source
Free Documentation Open-Source library Local deployment Basic LLM vulnerability scan using adversarial techniques from 2024 Basic RAG evaluation report using correctness metrics Best-effort maintenance Community support. For production LLM deployments: Enterprise - Book a Demo.
FAQs
Trending
