MirrorHub/synapse
0
0
Fork 1
mirror of https://mau.dev/maunium/synapse.git synced 2024-12-14 19:33:52 +01:00
Code Issues Projects Releases Wiki Activity

Strip overlong OpenGraph data from url preview

Browse source 
... to stop people causing DoSes with malicious web pages
This commit is contained in:
Richard van der Hoff 2019-11-05 15:45:17 +00:00
parent 9ffcf0f7ba
commit e9bfe719ba
3 changed files with 54 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
changelog.d/6331.feature Normal file
View file

@ -0,0 +1 @@
Limit the length of data returned by url previews, to prevent DoS attacks.

20
synapse/rest/media/v1/preview_url_resource.py
View file

@ -56,6 +56,9 @@ logger = logging.getLogger(__name__)
_charset_match = re.compile(br"<\s*meta[^>]*charset\s*=\s*([a-z0-9-]+)", flags=re.I) _charset_match = re.compile(br"<\s*meta[^>]*charset\s*=\s*([a-z0-9-]+)", flags=re.I)
_content_type_match = re.compile(r'.*; *charset="?(.*?)"?(;|$)', flags=re.I) _content_type_match = re.compile(r'.*; *charset="?(.*?)"?(;|$)', flags=re.I)
OG_TAG_NAME_MAXLEN = 50
OG_TAG_VALUE_MAXLEN = 1000
class PreviewUrlResource(DirectServeResource): class PreviewUrlResource(DirectServeResource):
isLeaf = True isLeaf = True
@ -167,7 +170,7 @@ class PreviewUrlResource(DirectServeResource):
ts (int): ts (int):
Returns: Returns:
Deferred[str]: json-encoded og data Deferred[bytes]: json-encoded og data
""" """
# check the URL cache in the DB (which will also provide us with # check the URL cache in the DB (which will also provide us with
# historical previews, if we have any) # historical previews, if we have any)
@ -268,6 +271,17 @@ class PreviewUrlResource(DirectServeResource):
logger.warn("Failed to find any OG data in %s", url) logger.warn("Failed to find any OG data in %s", url)
og = {} og = {}
# filter out any stupidly long values
keys_to_remove = []
for k, v in og.items():
if len(k) > OG_TAG_NAME_MAXLEN or len(v) > OG_TAG_VALUE_MAXLEN:
logger.warning(
"Pruning overlong tag %s from OG data", k[:OG_TAG_NAME_MAXLEN]
)
keys_to_remove.append(k)
for k in keys_to_remove:
del og[k]
logger.debug("Calculated OG for %s as %s" % (url, og)) logger.debug("Calculated OG for %s as %s" % (url, og))
jsonog = json.dumps(og) jsonog = json.dumps(og)
@ -502,6 +516,10 @@ def _calc_og(tree, media_uri):
og = {} og = {}
for tag in tree.xpath("//*/meta[starts-with(@property, 'og:')]"): for tag in tree.xpath("//*/meta[starts-with(@property, 'og:')]"):
if "content" in tag.attrib: if "content" in tag.attrib:
# if we've got more than 50 tags, someone is taking the piss
if len(og) >= 50:
logger.warning("skipping OG for page with too many og: tags")
return {}
og[tag.attrib["property"]] = tag.attrib["content"] og[tag.attrib["property"]] = tag.attrib["content"]
# TODO: grab article: meta tags too, e.g.: # TODO: grab article: meta tags too, e.g.:

34
tests/rest/media/v1/test_url_preview.py
View file

@ -247,6 +247,40 @@ class URLPreviewTests(unittest.HomeserverTestCase):
self.assertEqual(channel.code, 200) self.assertEqual(channel.code, 200)
self.assertEqual(channel.json_body["og:title"], "\u0434\u043a\u0430") self.assertEqual(channel.json_body["og:title"], "\u0434\u043a\u0430")
def test_overlong_title(self):
self.lookups["matrix.org"] = [(IPv4Address, "8.8.8.8")]
end_content = (
b"<html><head>"
b"<title>" + b"x" * 2000 + b"</title>"
b'<meta property="og:description" content="hi" />'
b"</head></html>"
)
request, channel = self.make_request(
"GET", "url_preview?url=http://matrix.org", shorthand=False
)
request.render(self.preview_url)
self.pump()
client = self.reactor.tcpClients[0][2].buildProtocol(None)
server = AccumulatingProtocol()
server.makeConnection(FakeTransport(client, self.reactor))
client.makeConnection(FakeTransport(server, self.reactor))
client.dataReceived(
(
b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n"
b'Content-Type: text/html; charset="windows-1251"\r\n\r\n'
)
% (len(end_content),)
+ end_content
)
self.pump()
self.assertEqual(channel.code, 200)
res = channel.json_body
self.assertCountEqual(["og:description"], res.keys())
def test_ipaddr(self): def test_ipaddr(self):
""" """
IP addresses can be previewed directly. IP addresses can be previewed directly.