Implement a content type allow list for URL previews (#11936)

This implements an allow list for content types for which Synapse will attempt URL preview. If a URL resolves to a resource with a content type which isn't in the list, the download will terminate immediately.

This makes sense given that Synapse would never successfully generate a URL preview for such files in the first place, and helps prevent issues with streaming media servers, such as #8302.

Signed-off-by: Denis Kasak dkasak@termina.org.uk

1 files changed, 8 insertions, 0 deletions

diff --git a/synapse/rest/media/v1/preview_url_resource.py b/synapse/rest/media/v1/preview_url_resource.py

index efd84ced8f..8d3d1e54dc 100644
--- a/synapse/rest/media/v1/preview_url_resource.py
+++ b/synapse/rest/media/v1/preview_url_resource.py
@@ -403,6 +403,7 @@ class PreviewUrlResource(DirectServeJsonResource):
                 output_stream=output_stream,
                 max_size=self.max_spider_size,
                 headers={"Accept-Language": self.url_preview_accept_language},
+                is_allowed_content_type=_is_previewable,
             )
         except SynapseError:
             # Pass SynapseErrors through directly, so that the servlet
@@ -761,3 +762,10 @@ def _is_html(content_type: str) -> bool:
 
 def _is_json(content_type: str) -> bool:
     return content_type.lower().startswith("application/json")
+
+
+def _is_previewable(content_type: str) -> bool:
+    """Returns True for content types for which we will perform URL preview and False
+    otherwise."""
+
+    return _is_html(content_type) or _is_media(content_type) or _is_json(content_type)