Safety classifications

One profile. No escape hatch — except a human.

  • read (navigation, assertions): always allowed
  • write-low (form input, drafts): allowed
  • write-high (delete, purchase, transfer): blocked by default — a human can approve one action, live

The runtime enforces a single policy profile (controlled-web). There is no CLI flag, environment variable, or API argument to weaken it — an agent can never trigger, skip, or pre-approve a blocked action. A person watching the cockpit can approve one specific action live, right when it happens; nothing else can. Sensitive input (passwords, credit cards) is blocked unless explicitly allowed per-call.

How it works

The gate is in the same process as the browser.

The safety check runs in the same V8 isolate as the executor. There's no way for an agent to bypass it — it can't skip the check, can't call the DOM directly, can't sneak past with a raw script. If the policy says block, the step doesn't execute, unless a human watching the cockpit approves that one action live. Every allow and every block — human-approved or automatic — is signed and logged.

The NLP compiler infers intent: "delete the user account" is classified as write-high and blocked under the default profile. "type my password" is blocked unless allowSensitiveInput: true is explicitly set.

VITRON-EA1 is designed as an open standard. Other runtimes can implement conformance via signed verification keys. Specification available on request.

Audit trail

Cryptographically chained evidence packs.

Each run produces a SHA-256 chained event log: every step, every policy decision, every DOM snapshot. Ed25519-signable, replayable, and reviewable. Built for regulated workflows where "trust me" is not a valid answer.

  • SHA-256 integrity hash per run
  • Ed25519 signable for non-repudiation
  • JSON-formatted for CI/CD consumption
  • Generated locally, never transmitted

For regulated environments

Air-gapped. Accessibility-aware.

A built-in WCAG 2.1 AA audit — running axe-core, the same engine behind Google Lighthouse's accessibility checks — with no external dependencies. Runs fully offline after the initial signed binary download.

  • WCAG 2.1 AA via axe-core, 100+ rules
  • Signed evidence pack per run
  • Air-gap deployable, zero telemetry

WCAG and NIST SP 800-53 audits are included free in the trial license bundled with every download — a commercial license removes the trial window. Email team@vitron.ai for one.