Benchmark your AI security readiness for 2027 → [Take the survey]

Benchmark your AI security readiness for 2027 → [Take the survey]

Benchmark your AI security readiness for 2027 → [Take the survey]

Home

/

Blog

/

Agentic AI Security

Agentic AI Security

GitBook Breach AI Agent Attacks

Inside the GitBook Breach: How an AI Agent Attack Reached Production in 5 Hours

A breakdown of the GitBook breach, the AI agent attack behind it, and how to secure AI agents and MCP connections.

4 Minutes

Saish Hindlekar

Saish Hindlekar

AI Red Teaming Solutions

AI Red Teaming Solutions: Choosing an Enterprise Platform or Service

Compare enterprise AI red teaming solutions - human-led, automated, and hybrid platforms - and what to evaluate before choosing one.

3 Minutes

Arpashree

Arpashree

Red Teaming AI Models

Red Teaming AI Models: Model Extraction, Data Poisoning and Jailbreak Testing

Learn how red teaming AI models works - testing for model extraction, data poisoning, and jailbreaks - and how it fits into a full security program.

4 Minutes

Arpashree

Arpashree

AI Security Data Sovereignty

AI Security Data Sovereignty: On-Prem vs. SaaS Evaluation Architectures

Compare on-prem and SaaS architectures for AI security tools - data sovereignty, CLOUD Act exposure, and questions to ask before you choose.

3 Minutes

Rushali

Rushali

AI Exposure Management

AI Exposure Management: Validating Reachable Agent Attack Paths

Learn what AI exposure management is, how it validates which agent attack paths are actually reachable, and how it differs from AI-SPM and red teaming

4 Minutes

Rushali

Rushali

DeepSeek and Frontier Model-Specific Security Risks

DeepSeek and Frontier Model-Specific Security Risks

Learn the documented security risks in DeepSeek and other frontier models - jailbreak susceptibility, agent hijacking, and how to evaluate any new model.

4 Minutes

Rushali

Rushali