Guardrails for AI on Company Data
September 10, 2026The control surfaces that actually contain damage once an agent is fooled: identity, permissions, audit trails, and prompt injection at the query layer.
2 posts tagged with "prompt injection"
Securing the Agentic Lakehouse Gateway: A Threat Model for Prompt Injection, Exfiltration, and the Firewall That Reads Sentences
August 19, 2026A threat model for the agentic lakehouse gateway covering prompt injection, exfiltration, and the firewall that reads sentences.