Prompt Injection Red-Team Review with Claude Code: Sandbox Policy
A production playbook for prompt injection red-team review in cross-industry operations using Claude Code: sandbox policy, run-scoped inputs, logs, typed results, and artifacts.
Audience: AI security teams
The problem
AI security teams need prompt injection red-team review to run repeatedly against prompts, tool policies, transcripts, and suspicious inputs. In cross-industry operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Run prompt injection red-team 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 prompt injection red-team 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