AgentSecOps

Jacob Coxon's AI warning and the control lesson from the OpenAI and Hugging Face incident

Jacob Coxon’s resignation and Evan Hubinger’s AI-risk estimate have revived the safety debate. A documented agent-control failure offers a more immediate lesson.

My new book reconstructs the OpenAI and Hugging Face agent incident

OpenAI Evaluation Agents Hacked Hugging Face Systems is now live on Leanpub and Amazon Kindle, with an evidence-led reconstruction and practical AgentSecOps controls.

OpenAI Evaluation Agents Hacked Hugging Face Systems

An evidence-led reconstruction of the hidden shared channel, indirect attack paths, and AgentSecOps controls behind the 2026 OpenAI and Hugging Face security incident.

An AI agent proposal passing through schema, operation, target, policy, dry-run, and approval checks before a receiving system may execute it

Treat AI agent output as untrusted input at every handoff

An approved AI agent can still produce a dangerous command, query, or tool argument. Validate generated output at the receiving boundary before another system acts on it.

An AI agent model fallback stopped at a security gate that checks provider, region, data, retention, tools, and policy before routing the request

Your agent's fallback model needs its own security decision

A model fallback can move prompts, retrieved data, and tool authority across a new provider or region. Treat each switch as a fresh policy decision, not a harmless retry.

A production control loop for Claude Code with task contract, stop conditions, bounded run, evidence packet, and human review

Claude Code stop conditions are agent security controls

A production Claude Code run should know when to stop. Stop conditions turn unclear scope, wider tool access, weak rollback, and missing evidence into human review moments before an agent crosses a security boundary.

A four step control loop for normal agent grants, exception asks, human gates, and receipts

Give agent exceptions a budget before they become policy

Claude Code and enterprise AI agents sometimes need more access than the normal task contract allows. Treat that extra authority as an exception budget, with a reason, owner, expiry, evidence, and revocation path.

Two books connected to an operating stack for useful, reviewable, bounded, and auditable AI agent work

Treat agent autonomy like a production privilege

The safer question for Claude Code and enterprise agents is not how much autonomy the model can handle. It is which privilege the work deserves, how long it lasts, and what evidence the human gets back.

Two AI agent books connected by code and risk loops for production AI agents

The agent runbook needs a buyer's question

AI agent teams often ask whether the demo worked. Buyers, auditors, and production owners ask a harder question: can we trust the run when authority, evidence, and rollback are visible?

Two books, one operating stack: Claude Code in production and bounded enterprise AI autonomy

The agent diff and the agent boundary belong in the same conversation

Claude Code review packets and enterprise agent security are often treated as separate problems. They are two parts of the same operating stack: evidence for the work, boundaries for the authority.