Facio Blog

Practical notes on human-reviewed AI agents.

Payload-powered product notes, security writing, HITL patterns, and operational guidance from the Facio runtime: long sessions, Placet approvals, audit trails, memory, providers, channels, tools, and Docker-first operations.

Clear

Showing 26-30 of 53 articles in Security.

Security

AI Agent Runtime Guardrails: Why Policy at the Model Layer Fails and Policy at the Execution Layer Wins

Jun 23, 2026Security

AI Agent Runtime Guardrails: Why Policy at the Model Layer Fails and Policy at the Execution Layer Wins

Static system prompts are advisory, not architectural. LLM guardrails operate at the same abstraction as the attack. The only deterministic defense is policy at the execution layer — where tool calls become real actions against real resources, with sub-millisecond evaluation.

Security

CVE-2026-2256: The First Agent-Runtime CVE That Should Change How You Deploy AI Agents

Jun 17, 2026Security

CVE-2026-2256: The First Agent-Runtime CVE That Should Change How You Deploy AI Agents

ModelScope's MS-Agent framework shipped a critical command injection vulnerability (CVSS 9.8) that turns any document, ticket, or email into a remote shell for attackers. No patch. Three months after disclosure. The procurement agent that approved $5M in fraudulent orders wasn't using a vulnerable framework — it was using any framework, the same way every agent does.