Banking KYC File Review with Claude Code: Sandbox Policy

A production playbook for banking KYC file review in banking operations using Claude Code: sandbox policy, run-scoped inputs, logs, typed results, and artifacts.

Audience: Bank compliance teams reviewing customer onboarding

The problem

Bank compliance teams reviewing customer onboarding need banking KYC file review to run repeatedly against KYC forms, IDs, beneficial ownership records, sanctions notes, and risk policies. In banking operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.

Implementation path

Run banking KYC file review in an ephemeral sandbox, keep provider credentials in the broker, expose narrow tools, and store logs outside the workspace for review.

Tradeoffs and failure modes

A narrower runtime blocks ambient machine behavior, but it gives security reviewers a concrete boundary. For banking KYC file review, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.

Runtime boundary

filesystem: /skill and /skill/.argo/inputs only
network: deny by default
artifacts: /skill/output/artifacts
logs: retained outside sandbox
provider: Claude Code

Run this on Argo