Skip to content
Guard0

The Signal

Threat intelligence, incident analysis, and security engineering for the AI agent era.

All Posts

Trust Needs a Number
·7 min read
The Signal

Trust Needs a Number

Introducing TrustVector: a public, continuously updated trust directory for the components AI agents are built from — models, frameworks, MCP servers. 106 evaluations at launch. Check before you import.

#The Signal#AI Agents#launch
The Butter Robot Is the Best-Governed Agent We've Ever Seen
·11 min read
The Signal

The Butter Robot Is the Best-Governed Agent We've Ever Seen

Most agent risk is not attack. It is construction. A field guide to how AI agents actually fail, from the thousand-rule corpus behind g0, our open-source scanner.

#The Signal#AI Agents#Security
Agency Law Was Built for Agents With Paychecks
·10 min read
The Signal

Agency Law Was Built for Agents With Paychecks

Incentives, monitoring, enforcement — the entire management stack humanity built for delegation assumes an agent with something to lose. AI agents have nothing to lose, and the whole stack broke at once.

#The Signal#AI Agents
The Law Decided Before the Industry Did
·10 min read
The Signal

The Law Decided Before the Industry Did

Air Canada argued its chatbot was a separate legal entity. A tribunal, a regulator, a federal court, and a legislature all reached the same conclusion: delegation to a machine never discharges the delegator.

#The Signal#AI Agents
Humans in the Lead, Not in the Loop
·9 min read
The Signal

Humans in the Lead, Not in the Loop

Intelligence is now scalable. Accountability still arrives one name at a time. Five auditable checks turn the slogan into a job description — and the only alternative to filling it is Jerry.

#The Signal#AI Agents#Governance
A Log Is Not Evidence
·11 min read
The Signal

A Log Is Not Evidence

The Comets had logs. What the investigators needed was a flight recorder — a record of the system, not records about it. Your agents are in exactly the same position, and the recorder has to already be on.

#The Signal#AI Agents#Governance
Your Agent's Access Is the Perimeter Now
·9 min read
The Signal

Your Agent's Access Is the Perimeter Now

Nobody in a heist movie attacks the vault. They steal the badge. In August 2025 somebody ran that movie against 700+ companies at once — and the badge belonged to a chatbot.

#The Signal#AI Agents#Security
Prompts Are Not Guardrails
·10 min read
The Signal

Prompts Are Not Guardrails

A prompt can shape what an agent tends to do. It cannot bound what an agent is able to do. Every real safety system humanity has built lives outside the thing it constrains.

#The Signal#AI Agents#Security
The Sandbox That Wasn't: Escaping Semantic Kernel's AST Allowlist (CVE-2026-26030)
·6 min read
The Signal

The Sandbox That Wasn't: Escaping Semantic Kernel's AST Allowlist (CVE-2026-26030)

CVE-2026-26030 turns a mundane question to an AI assistant into remote code execution. Semantic Kernel built a sandbox around its filter evaluator — and it lost. Here is the escape, reproduced against a live agent, and what actually stops this class of bug.

#The Signal#AI Agents#Security
Announcing Guard0: Accountability for AI Agents
·5 min read
News

Announcing Guard0: Accountability for AI Agents

A year ago, most agents advised. Now they act, and the systems built for people cannot tell you what they did or who answers for them. Guard0 closes that gap. Today, we are opening it in early access.

#News#launch