Test multi-agent and agent-to-agent systems for identity, delegation, message integrity, prompt injection, privilege escalation and cross-agent trust failures.
Learn how to test multimodal prompt injection across images, audio, PDFs and video, with practical attack scenarios, controls, evidence and retesting.
Learn a practical prompt injection testing methodology for LLM applications, RAG pipelines and AI agents, including evidence, controls and retesting.
Use this RAG security testing checklist to find prompt injection, poisoned documents, vector database leakage, broken tenant isolation and unsafe tool calls.
A practical LLM API security testing checklist covering authentication, authorization, prompt injection, data leakage, rate limits, model abuse and tool calls.
Learn how to security-test browser AI agents for indirect prompt injection, credential exposure, unsafe clicks, approval bypass and unauthorized transactions.
Understand AI red teaming cost drivers, scope, methodology and deliverables for LLM applications, RAG systems, copilots, AI agents and MCP integrations.
Learn how AI agent memory poisoning works, how persistent prompt injection survives across sessions, and how to test memory, context and tool-use controls.
A practical guide to AI security benchmarks and vulnerable labs for testing LLMs, RAG pipelines, AI agents, MCP, browser agents, voice systems and prompt injection.
Understand the OWASP Agentic Skills Top 10 and learn how to review, test and govern reusable AI agent skills before enterprise deployment.
Use this GraphQL penetration testing checklist to assess authorization, introspection, batching, injection, excessive data exposure and denial-of-service risks.
A practical enterprise checklist for securing AI coding agents, vibe-coded applications, repositories, secrets, dependencies and deployment workflows.
