deepseek-harness/packages/client/connection/src/api-request-trust.ts

/**
 * Browser-trust fence for every /api request. Defends the two confused-deputy
 * paths a browser opens against a local HTTP API — DNS rebinding (Host names
 * the attacker's domain while the socket reaches this server) and cross-site
 * requests fired from a malicious page — without blocking non-browser clients
 * (no browser markers → no deputy to confuse, and a native client forges Host
 * freely anyway) or legitimately remote browsers (their authority is declared
 * via `trustedHosts`, or derived by the composing app for IP-literal LAN
 * serving). Network reachability and authentication stay out of scope: binding
 * policy belongs to the webserver config, and this fence is not an auth layer.
 */

import type { IncomingHttpHeaders } from 'node:http'

/** The request facts the fence reads (structural subset of IncomingMessage). */
interface ApiTrustRequest {
  headers: IncomingHttpHeaders
}

function header(headers: IncomingHttpHeaders, name: string): string | undefined {
  const value = headers[name]
  return typeof value === 'string' ? value : undefined
}

function isLoopbackHostname(hostname: string): boolean {
  if (hostname === 'localhost' || hostname === '[::1]') return true
  const parts = hostname.split('.')
  return parts.length === 4
    && parts[0] === '127'
    && parts.every(part => /^\d{1,3}$/.test(part) && Number(part) <= 255)
}

/** Normalized URL of a Host-header authority (hostname lowercased, default port stripped, IPv6 bracketed), or undefined when unparsable. */
function parseAuthority(authority: string): URL | undefined {
  try {
    // http: is a WHATWG "special scheme": parsing yields a non-empty hostname or throws.
    return new URL(`http://${authority}`)
  } catch {
    return undefined
  }
}

/**
 * Whether the request authority matches a `trustedHosts` entry. An entry with
 * an explicit port matches that exact authority; a port-less entry matches the
 * hostname on any port (the shape the CLI derives for IP-literal LAN serving,
 * where the bound port may be OS-assigned). Both sides compare through WHATWG
 * normalization, so case and a redundant `:80` never decide trust.
 */
function isTrustedAuthority(hostUrl: URL, trustedHosts: readonly string[]): boolean {
  return trustedHosts.some((entry) => {
    const entryUrl = parseAuthority(entry)
    if (entryUrl === undefined) return false
    return /:\d+$/.test(entry)
      ? entryUrl.host === hostUrl.host
      : entryUrl.hostname === hostUrl.hostname
  })
}

/**
 * Decide whether one /api request may reach the RPC bridge.
 * @param request - node HTTP request facts (headers).
 * @param trustedHosts - non-loopback authorities this deployment serves: exact `host:port`, or port-less `host` matching any port.
 * @returns true for requests without browser markers, and for browser requests whose Host is ours and whose markers are same-origin.
 */
export function isTrustedApiRequest(request: ApiTrustRequest, trustedHosts: readonly string[]): boolean {
  // Marker gate: Origin and sec-fetch-site exist only when a browser is the
  // sender's deputy. Absent both, the sender is the principal itself (curl,
  // tests, native shells) and could forge every header below — fencing it
  // would add nothing and would break non-browser LAN automation.
  const origin = header(request.headers, 'origin')
  const secFetchSite = header(request.headers, 'sec-fetch-site')
  if (origin === undefined && secFetchSite === undefined) return true
  // Host fence (DNS-rebinding defense): the browser fills Host from the URL it
  // believes it is talking to, so a rebound page carries the attacker's domain
  // here even though the socket lands on this server.
  const host = header(request.headers, 'host')
  if (host === undefined) return false
  const hostUrl = parseAuthority(host)
  if (hostUrl === undefined) return false
  if (!isLoopbackHostname(hostUrl.hostname) && !isTrustedAuthority(hostUrl, trustedHosts)) return false
  // Cross-site fence: modern browsers label the initiator relationship on
  // every fetch; an explicit cross-site marker is refused regardless of Origin.
  if (secFetchSite === 'cross-site') return false
  // Origin fence: when a browser attaches an Origin it must be exactly this
  // authority (compared through the same normalization as the Host). The
  // literal "null" (sandboxed iframes, file: pages) is an opaque origin, refused.
  if (origin === undefined) return true
  try {
    return new URL(origin).host === hostUrl.host
  } catch {
    return false
  }
}