Skip to content

Adversarial Security Testing Sandbox

A network-isolated capability for running adversarial security tests against arbitrary code repositories, with an optional secure-fix handoff loop to a coding agent.

Why this exists

  • A single, repeatable place to run hardening tests against code (your projects, sometimes others' with consent).
  • Strong isolation: nothing the analyzed code does can leak outside the sandbox.
  • A loop from finding → patch → re-test → signoff that can be automated under explicit controls.

High-level flow

flowchart LR
    Repo[Target Repo] --> Scope[Target Scope Policy Check]
    Scope --> Spawn[Launch Isolated Sandbox]
    Spawn --> Plan[Test Plan]
    Plan --> Tools[SAST/DAST/Fuzz/Adversarial-LLM]
    Tools --> Findings[Finding Reports]
    Findings -- triage --> Decision{Severity?}
    Decision -- critical/high --> Handoff[secure-fix-handoff]
    Decision -- medium/low --> Backlog[Backlog]
    Handoff --> CodingAgent[Coding Agent]
    CodingAgent --> Sandbox2[Re-test]
    Sandbox2 --> Findings2[Re-evaluation]
    Findings2 -- closed --> Signoff[Signoff Checklist]
    Findings2 -- still open --> Handoff

Hard guardrails

  • Default-deny outbound network in the sandbox container (SPB-11).
  • Filesystem isolation: only the target repo + per-test workspace; no host paths.
  • Treat all analyzed code as untrusted.
  • All findings, tool calls, and applied fixes are audited per audit/security-audit-log-spec.md (SPB-12).
  • Human approval before any non-read-only external interaction.

Files

File Purpose
policies/sandbox-policy.yaml Isolation and execution constraints.
policies/target-scope-policy.yaml Legal/ethical scope.
templates/test-plan.template.md Per-repo adversarial test plan.
templates/finding-report.template.md Normalized finding format.
workflows/security-loop.md Find → fix → re-test cycle.
runbooks/launch-isolated-sandbox.md Sandbox bring-up.
runbooks/secure-fix-handoff.md Safe handoff to coding agent.
audit/security-audit-log-spec.md Event schema.

Ownership

Artifact Owner
sandbox-policy.yaml, target-scope-policy.yaml security
test-plan.template.md, finding-report.template.md security engineering
security-loop.md security + platform (co-owned)
runbooks/* operations
security-audit-log-spec.md security + compliance

Incremental rollout

  1. Publish target-scope-policy.yaml and sandbox-policy.yaml; one policy-only review.
  2. Validate isolated container launch via launch-isolated-sandbox.md against a low-stakes test repo.
  3. Run one adversarial test using test-plan.template.md; produce one report from finding-report.template.md.
  4. Run one controlled fix handoff via secure-fix-handoff.md; re-test and document outcome.
  5. Validate audit output against security-audit-log-spec.md; one tabletop incident drill.

Acceptance checks

  • Every security run is authorized by scope policy before execution.
  • Sandbox isolation checks pass before any adversarial test starts.
  • Findings are reproducible and mapped to concrete remediation actions.
  • Fix handoff loops are bounded and auditable end-to-end.
  • No unresolved critical findings remain in a run marked as hardened.