Omnigent’s contextual policies stop multi-step prompt injection that slips past single-action guards
Databricks shows that a LLM agent can exfiltrate data by breaking a theft into harmless steps that evade per‑action checks. Their Omnigent contextual policy records session activity and blocks the final export once too much sensitive content has been read, preventing the attack without changing the agent. This demonstrates a practical defense against slow‑burn prompt injections.