Confine CardDAV requests to configured origins

src/govoplan_addresses/backend/carddav.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import base64
+import posixpath
 import urllib.error
 import urllib.parse
 import urllib.request
@@ -269,7 +270,19 @@ class AddressCardDAVClient:
         return AddressCardDAVWriteResult(href=href, etag=response_etag(response_headers), status=status)
 
     def object_url(self, href: str) -> str:
-        return urllib.parse.urljoin(self.collection_url, href)
+        candidate = same_origin_dav_url(
+            self.collection_url,
+            href,
+            label="CardDAV object href",
+        )
+        collection_parts = urllib.parse.urlparse(self.collection_url)
+        candidate_parts = urllib.parse.urlparse(candidate)
+        collection_path = posixpath.normpath(urllib.parse.unquote(collection_parts.path))
+        candidate_path = posixpath.normpath(urllib.parse.unquote(candidate_parts.path))
+        collection_prefix = collection_path.rstrip("/") + "/"
+        if not candidate_path.startswith(collection_prefix) or candidate_path == collection_path:
+            raise AddressCardDAVError("CardDAV object href must remain inside the configured collection path")
+        return candidate
 
     def request(self, method: str, url: str, *, body: bytes | None, depth: str | None, expected: set[int]) -> bytes:
         _status, _headers, payload = self.request_raw(method, url, body=body, depth=depth, expected=expected)
@@ -313,8 +326,14 @@ class AddressCardDAVClient:
 def urllib_transport(method: str, url: str, headers: Mapping[str, str], body: bytes | None, timeout: int) -> tuple[int, Mapping[str, str], bytes]:
     url = validate_http_url(url)
     try:
-        request = urllib.request.Request(url, data=body, headers=dict(headers), method=method)
-        with urllib.request.urlopen(request, timeout=timeout) as response:  # noqa: S310 - validated CardDAV HTTP(S) URL.  # nosec B310
+        request = urllib.request.Request(  # noqa: S310 - URL is validated and origin-confined.
+            url,
+            data=body,
+            headers=dict(headers),
+            method=method,
+        )
+        opener = urllib.request.build_opener(_SameOriginRedirectHandler(url))
+        with opener.open(request, timeout=timeout) as response:  # noqa: S310 - validated CardDAV URL; redirects remain on origin.  # nosec B310
             return response.status, dict(response.headers.items()), response.read()
     except urllib.error.HTTPError as exc:
         return exc.code, dict(exc.headers.items()), exc.read()
@@ -431,16 +450,72 @@ def ensure_collection_url(value: str) -> str:
 
 
 def validate_http_url(value: str) -> str:
-    parsed = urllib.parse.urlparse(value)
-    if parsed.scheme not in {"http", "https"} or not parsed.netloc:
+    parsed = urllib.parse.urlparse(value.strip())
+    if parsed.scheme.lower() not in {"http", "https"} or not parsed.netloc or not parsed.hostname:
         raise AddressCardDAVError("CardDAV URL must be an absolute HTTP(S) URL")
     if parsed.username or parsed.password:
         raise AddressCardDAVError("CardDAV URL must not include embedded credentials")
+    if parsed.query or parsed.fragment:
+        raise AddressCardDAVError("CardDAV URL must not include a query or fragment")
+    _url_origin(parsed)
     return urllib.parse.urlunparse(parsed)
 
 
 def absolute_dav_url(base_url: str, href: str) -> str:
-    return urllib.parse.urljoin(ensure_collection_url(base_url), href)
+    return same_origin_dav_url(base_url, href, label="CardDAV discovery href")
+
+
+def same_origin_dav_url(base_url: str, href: str, *, label: str) -> str:
+    base = ensure_collection_url(base_url)
+    candidate = validate_http_url(urllib.parse.urljoin(base, href))
+    if _url_origin(urllib.parse.urlparse(candidate)) != _url_origin(urllib.parse.urlparse(base)):
+        raise AddressCardDAVError(f"{label} must use the configured collection origin")
+    return candidate
+
+
+def _url_origin(parsed: urllib.parse.ParseResult) -> tuple[str, str, int]:
+    try:
+        port = parsed.port
+    except ValueError as exc:
+        raise AddressCardDAVError("CardDAV URL has an invalid port") from exc
+    scheme = parsed.scheme.lower()
+    if port is None:
+        port = 443 if scheme == "https" else 80
+    return scheme, (parsed.hostname or "").lower(), port
+
+
+class _SameOriginRedirectHandler(urllib.request.HTTPRedirectHandler):
+    def __init__(self, source_url: str) -> None:
+        super().__init__()
+        self._source_origin = _url_origin(urllib.parse.urlparse(validate_http_url(source_url)))
+
+    def redirect_request(self, req, fp, code, msg, headers, newurl):  # type: ignore[no-untyped-def]
+        del fp, msg, headers
+        try:
+            candidate = validate_http_url(newurl)
+        except AddressCardDAVError:
+            return None
+        if _url_origin(urllib.parse.urlparse(candidate)) != self._source_origin:
+            return None
+        method = req.get_method()
+        data = req.data
+        if code == 303 and method != "HEAD":
+            method, data = "GET", None
+        elif code in {301, 302} and method == "POST":
+            method, data = "GET", None
+        forwarded_headers = {
+            key: value
+            for key, value in req.header_items()
+            if key.casefold() not in {"host", "content-length"}
+        }
+        return urllib.request.Request(  # noqa: S310 - candidate is validated and same-origin.
+            candidate,
+            data=data,
+            headers=forwarded_headers,
+            origin_req_host=req.origin_req_host,
+            unverifiable=True,
+            method=method,
+        )
 
 
 def strip_weak_etag(value: str | None) -> str | None:

src/govoplan_addresses/backend/router.py

@@ -618,7 +618,7 @@ def api_discover_carddav_address_books(
     principal: ApiPrincipal = Depends(get_api_principal),
     session: Session = Depends(get_session),
 ):
-    _require_scope(principal, "addresses:sync:read")
+    _require_scope(principal, "addresses:sync:write")
     try:
         address_books = discover_carddav_address_books(session, principal, payload)
         return AddressCardDavDiscoveryResponse(