Skip to main content

Security & scope

Every pentest agent executes inside an isolated sandbox with controlled network egress. This keeps the run safe against live and staging applications, and it means AISafe never touches your source code in this service.

Sandbox isolation​

Each agent runs in a constrained execution environment:

  • Isolated. The agent's environment shares no filesystem or memory with other sandboxes or the host.
  • Controlled network access. For pentests, the sandbox reaches the target URLs you provide plus additional allowed domains. It reaches no others.
  • Ephemeral. The platform destroys the sandbox when the assessment completes (or times out). No state persists between assessments.

Even if an agent misbehaves, it cannot cause harm outside its assigned task. See Sandbox isolation.

No source access​

In the black-box pentest, AISafe accesses only the live behavior of your application. It does not receive or inspect your source code. For source-level analysis and its associated isolation, see Source Code Audit.

Controlled egress​

AISafe's sandbox network policy prevents data exfiltration and limits blast radius:

  • The sandbox reaches the target URLs you provide, and no others.
  • The platform blocks any host not in your allowlist.
  • You can add allowed domains if your application makes cross-origin requests.

The agent cannot reach unintended internal services or third-party systems.

Scope boundaries​

The agent operates within the scope you define. Any URL outside the provided target URLs (and additional allowed domains) is unreachable from the sandbox.

If the agent meets a redirect to a domain outside your configured scope, it does not follow it. This keeps the test in bounds even when the application links to external services.

The crawl also respects any excluded paths and rate limits you set, so you can shield sensitive endpoints and avoid destructive actions.

Credential handling​

AISafe destroys the sandbox after the pentest completes. No artifacts from the run — credentials, session tokens, or captured responses — persist beyond the assessment. Use a dedicated test account rather than a real one, since the agents hold it for the duration of the run only.

What this means for you​

  • Your source code never leaves your control and is not used by this service.
  • Agents cannot reach your internal services during the pentest.
  • Nothing persists after the run ends.
  • The test stops where your scope stops, including redirects to outside hosts.

AISafe cannot reach your internal network, does not follow redirects outside scope, and destroys every sandbox when the assessment finishes.