12 section

Security & Access

The LLM-specific attack surface — injection through retrieved content, extraction, unsafe tool output — plus the access-control machinery that keeps one tenant's data out of another tenant's answers.

2 pages 16 min 3,302 words

01 the section

What is in here

Read LLM Security first: it explains why prompt injection is not solvable by prompting, and maps the threats onto the OWASP LLM Top 10. Access Control then covers the parts an audit actually checks — RBAC and ABAC, tenant filtering at the vector store, key rotation, audit logs. The Multi-Tenant SaaS case study is the applied version of both.