Allow only http(s) URLs from feeds and OPML, at storage and render (R2-S1, #33)

A feed's channel link, an entry's link and an OPML htmlUrl were stored
as given and rendered in href attributes (bulk writes skip model
validation), so a malicious feed could supply a javascript: or data:
link. CSP is a second layer, not the control.

apps.core.urlutils accepts only absolute http(s) URLs. Fetching stores
channel/entry links through it — relative links now resolve against the
feed's own URL instead of being stored as dead relative paths — OPML
import skips non-http(s) feed URLs and blanks unsafe htmlUrl, and the
add-feed form rejects non-http(s) (URLField also allows ftp). A
safe_http_url template filter guards the two places a feed-supplied URL
becomes a link (the article's "Original" link and the dashboard), so
values already in the database from before this fix are neutralized too.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
ksmithandClaude Sonnet 5.5 committed 2026-11-01 11:57:23 -07:00
1 parent 85914f9107
commit 41f99e9405
13 files changed
+192 -7

No files matched your search

View File
Whitespace-only changes.
+12
View File
@@ -0,0 +1,12 @@
from django import template
from apps.core.urlutils import http_url_or_empty
register = template.Library()
@register.filter
def safe_http_url(value):
""" "" unless value is an absolute http(s) URL — use before putting any
feed-supplied URL in an href (see apps.core.urlutils)."""
return http_url_or_empty(value)
+44
View File
@@ -0,0 +1,44 @@
import pytest
from django.template import Context, Template
from .urlutils import http_url_or_empty, resolve_http_url
@pytest.mark.parametrize(
"value",
[
"javascript:alert(1)",
"JaVaScRiPt:alert(1)",
"java\tscript:alert(1)",
" javascript:alert(1)",
"data:text/html,<script>alert(1)</script>",
"vbscript:msgbox(1)",
"file:///etc/passwd",
"ftp://example.com/feed.xml",
"//example.com/no-scheme",
"/relative/path",
"http://",
"",
None,
],
)
def test_unsafe_or_non_absolute_urls_are_rejected(value):
assert http_url_or_empty(value) == ""
@pytest.mark.parametrize("value", ["http://example.com/a", "https://example.com/a?b=1#c"])
def test_http_and_https_urls_pass_through(value):
assert http_url_or_empty(value) == value
def test_relative_links_resolve_against_the_feed_url_and_are_still_checked():
base = "https://blog.example.com/feed.xml"
assert resolve_http_url(base, "/2026/post") == "https://blog.example.com/2026/post"
assert resolve_http_url(base, "javascript:alert(1)") == ""
assert resolve_http_url(base, "https://other.example.com/x") == "https://other.example.com/x"
def test_template_filter_blanks_unsafe_urls():
template = Template("{% load safe_urls %}[{{ url|safe_http_url }}]")
assert template.render(Context({"url": "javascript:alert(1)"})) == "[]"
assert template.render(Context({"url": "https://example.com/"})) == "[https://example.com/]"
+30
View File
@@ -0,0 +1,30 @@
from urllib.parse import urljoin, urlsplit
ALLOWED_SCHEMES = {"http", "https"}
def http_url_or_empty(value: str | None) -> str:
"""The URL if it's an absolute http(s) URL, else "". Feed content is
untrusted: a link of "javascript:..." or "data:..." is harmless inside
an escaped attribute value but becomes script the moment someone
clicks it, so every URL we store from a feed or OPML file, and every
one we render as a link, goes through this. (urlsplit already ignores
the tab/newline tricks browsers also ignore inside a scheme.)"""
if not value:
return ""
value = value.strip()
try:
parts = urlsplit(value)
except ValueError:
return ""
if parts.scheme.lower() not in ALLOWED_SCHEMES or not parts.netloc:
return ""
return value
def resolve_http_url(base: str, value: str | None) -> str:
"""Like http_url_or_empty, but first resolves a relative link (feeds
often give "/2026/post") against the feed's own URL."""
if not value:
return ""
return http_url_or_empty(urljoin(base, value.strip()))