November 9, 2026 · Edition #40 · by Asaf Nakash
Contain first, then fix
I think we should build software that can lose a dangerous capability without losing every useful service it provides. When a vulnerability appears, the response should not automatically be a choice between shutting down the application and leaving all its powers intact.
Consider an expense application. During a repair, it could still let employees view receipts and prepare claims, while payments, bulk data exports and changes to approval permissions are suspended. Route any operation that must continue through a separate verification gate, and revoke the application's direct access so it cannot bypass that route. The gate must sit outside the vulnerable component, enforcing rules and identities the component cannot rewrite.
If an application cannot disable an individual action or tool, we should build it to do so. The ability to withdraw a capability should be a design requirement, not something security teams have to invent during an incident. This means treating software as code plus the actions it is authorized to perform, and designing those actions to be independently controlled.
Red Hat's networking flaw shows why that control has to match the actual vulnerability: disabling one related feature does not remove the flaw, and packet filtering only reduces exposure. The goal is to keep a defensible subset of service available, not to declare an application safe because somebody found a switch. Some flaws will still require a shutdown.
Agents can connect this containment to repair. OpenAI's Linux pipeline already generates candidate patches and exploitability evidence for human review. I want the next steps connected too: validate the fix, prepare an authorized staged rollout, collect compatibility evidence, obtain approval to expand it, and verify the fixed version is running. A healthy canary alone does not prove the vulnerability is gone.
Feature switches and approval workflows already exist. The change I am arguing for is making revocable actions part of the architecture, with a repair path that restores them. Build applications that can keep serving while their most consequential powers are withheld.
Written by Asaf Nakash, Principal Product Manager for AI Security at Microsoft Defender and host of the Context Window podcast. Originally published in Context Window Edition #40, November 9, 2026.