A structured methodology for red teaming large language model applications — covering attack taxonomy, scoping, tooling (Garak, PyRIT, PromptBench), and how to translate findings into actionable security improvements.
Threat actors are embedding prompt injection payloads in third-party LLM plugins and data sources to hijack AI agent actions, exfiltrate data, and pivot within enterprise environments.
A practical framework for implementing prompt injection detection and containment at the API gateway layer — covering input sanitisation, context isolation, output filtering, and anomaly-based detection for production LLM deployments.
Practical design patterns for building a prompt injection and jailbreak detection layer in front of production LLM deployments — covering rule-based filters, semantic classifiers, canary tokens, and output validation.
Analysis of a novel attack class targeting agentic AI systems: how injected instructions in tool outputs can escalate an agent's effective permissions, exfiltrate data, and pivot to internal services — and how to defend against it.