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()))
+11
View File
@@ -1,10 +1,21 @@
from django import forms from django import forms
from apps.core.urlutils import http_url_or_empty
from .models import Subscription from .models import Subscription
class AddFeedForm(forms.Form): class AddFeedForm(forms.Form):
feed_url = forms.URLField(label="Feed URL", max_length=1000, assume_scheme="https") feed_url = forms.URLField(label="Feed URL", max_length=1000, assume_scheme="https")
def clean_feed_url(self):
# URLField also accepts ftp:// and ftps://; feeds are only ever
# fetched over http(s).
url = http_url_or_empty(self.cleaned_data["feed_url"])
if not url:
raise forms.ValidationError("Enter a feed URL starting with http:// or https://.")
return url
tag_names = forms.CharField( tag_names = forms.CharField(
label="Tags", label="Tags",
max_length=500, max_length=500,
+5 -2
View File
@@ -17,6 +17,7 @@ from io import BytesIO
import defusedxml.ElementTree as DefusedET import defusedxml.ElementTree as DefusedET
from apps.articles.models import SubscriptionTag, Tag from apps.articles.models import SubscriptionTag, Tag
from apps.core.urlutils import http_url_or_empty
from .models import Feed, Subscription from .models import Feed, Subscription
@@ -66,7 +67,9 @@ def parse_opml(file_obj) -> list[dict]:
def walk(container, ancestor_names): def walk(container, ancestor_names):
for outline in container.findall("outline"): for outline in container.findall("outline"):
xml_url = outline.get("xmlUrl") xml_url = http_url_or_empty(outline.get("xmlUrl"))
if outline.get("xmlUrl") and not xml_url:
continue # a feed URL that isn't http(s) can never be fetched
if xml_url: if xml_url:
tag_names = list(ancestor_names) tag_names = list(ancestor_names)
category_attr = outline.get("category") category_attr = outline.get("category")
@@ -79,7 +82,7 @@ def parse_opml(file_obj) -> list[dict]:
{ {
"feed_url": xml_url, "feed_url": xml_url,
"title": outline.get("title") or outline.get("text") or "", "title": outline.get("title") or outline.get("text") or "",
"site_url": outline.get("htmlUrl") or "", "site_url": http_url_or_empty(outline.get("htmlUrl")),
"tag_names": tag_names, "tag_names": tag_names,
} }
) )
+3 -2
View File
@@ -23,6 +23,7 @@ from django.utils import timezone
from apps.articles.models import Article, PurgedArticle from apps.articles.models import Article, PurgedArticle
from apps.core.models import SiteSettings from apps.core.models import SiteSettings
from apps.core.urlutils import resolve_http_url
from apps.feeds.models import Feed from apps.feeds.models import Feed
from .ssrf_guard import SSRFBlocked, safe_get from .ssrf_guard import SSRFBlocked, safe_get
@@ -222,7 +223,7 @@ def fetch_and_ingest(feed: Feed) -> FetchResult:
channel_title = parsed.feed.get("title") channel_title = parsed.feed.get("title")
if channel_title and not feed.title: if channel_title and not feed.title:
feed.title = channel_title[:500] feed.title = channel_title[:500]
channel_link = parsed.feed.get("link") channel_link = resolve_http_url(feed.feed_url, parsed.feed.get("link"))
if channel_link and not feed.site_url: if channel_link and not feed.site_url:
feed.site_url = channel_link[:1000] feed.site_url = channel_link[:1000]
@@ -249,7 +250,7 @@ def fetch_and_ingest(feed: Feed) -> FetchResult:
if guid in parsed_entries: if guid in parsed_entries:
continue continue
title = (getattr(entry, "title", "") or "")[:1000] title = (getattr(entry, "title", "") or "")[:1000]
link = (getattr(entry, "link", "") or "")[:2000] link = resolve_http_url(feed.feed_url, getattr(entry, "link", ""))[:2000]
author = (getattr(entry, "author", "") or "")[:500] author = (getattr(entry, "author", "") or "")[:500]
summary = (getattr(entry, "summary", "") or "")[:5000] summary = (getattr(entry, "summary", "") or "")[:5000]
content_html = sanitize_html(_entry_content_html(entry)) content_html = sanitize_html(_entry_content_html(entry))
+24
View File
@@ -399,3 +399,27 @@ def test_old_entries_are_ingested_normally_when_retention_is_off(feed):
responses.add(responses.GET, FEED_URL, body=xml, status=200) responses.add(responses.GET, FEED_URL, body=xml, status=200)
assert len(fetch_and_ingest(feed).new_article_ids) == 1 assert len(fetch_and_ingest(feed).new_article_ids) == 1
@pytest.mark.django_db
@responses.activate
def test_unsafe_urls_in_a_feed_are_not_stored(feed):
"""R2-S1: a feed's channel link and entry links are untrusted — only
absolute http(s) URLs may be persisted (they end up in href attributes)."""
xml = (
'<?xml version="1.0"?><rss version="2.0"><channel><title>T</title>'
"<link>javascript:alert(1)</link>"
"<item><title>Bad</title><guid>bad</guid><link>javascript:alert(2)</link></item>"
"<item><title>Relative</title><guid>rel</guid><link>/posts/1</link></item>"
"<item><title>Good</title><guid>good</guid><link>https://example.com/good</link></item>"
"</channel></rss>"
)
responses.add(responses.GET, FEED_URL, body=xml, status=200)
fetch_and_ingest(feed)
assert feed.site_url == ""
links = dict(Article.objects.filter(feed=feed).values_list("guid", "link"))
assert links["bad"] == ""
assert links["rel"] == "https://example.com/posts/1"
assert links["good"] == "https://example.com/good"
+18
View File
@@ -192,3 +192,21 @@ class TestExportOPML:
exported = export_opml(alice) exported = export_opml(alice)
assert b"<opml" in exported assert b"<opml" in exported
assert b"<outline" not in exported assert b"<outline" not in exported
class TestUnsafeOPMLUrls:
def test_non_http_feed_urls_are_skipped_and_unsafe_html_urls_blanked(self):
from io import BytesIO
from apps.feeds.opml import parse_opml
xml = b"""<?xml version="1.0"?><opml version="2.0"><head/><body>
<outline text="Bad" xmlUrl="javascript:alert(1)"/>
<outline text="FTP" xmlUrl="ftp://example.com/feed.xml"/>
<outline text="Good" xmlUrl="https://example.com/feed.xml" htmlUrl="javascript:alert(2)"/>
</body></opml>"""
entries = parse_opml(BytesIO(xml))
assert [e["feed_url"] for e in entries] == ["https://example.com/feed.xml"]
assert entries[0]["site_url"] == ""
+11
View File
@@ -117,3 +117,14 @@ def test_add_feed_view_rejects_duplicate_subscription(client, two_users):
assert response.status_code == 302 assert response.status_code == 302
assert Subscription.objects.filter(user=alice, feed=feed).count() == 1 assert Subscription.objects.filter(user=alice, feed=feed).count() == 1
@pytest.mark.django_db
@pytest.mark.parametrize("url", ["ftp://example.com/feed.xml", "javascript:alert(1)"])
def test_add_feed_rejects_non_http_urls(client, two_users, url):
client.login(username="alice", password="pw-alice-123")
response = client.post(reverse("feeds:add_feed"), {"feed_url": url})
assert response.status_code == 200
assert not Feed.objects.filter(feed_url=url).exists()
+30
View File
@@ -554,3 +554,33 @@ def test_authenticated_pages_load_the_tab_badge_script_with_its_endpoint(client,
assert f'data-url="{reverse("reader:new_since")}"' in content assert f'data-url="{reverse("reader:new_since")}"' in content
client.logout() client.logout()
assert "tab-badge" not in client.get(reverse("accounts:login")).content.decode() assert "tab-badge" not in client.get(reverse("accounts:login")).content.decode()
@pytest.mark.django_db
def test_unsafe_stored_links_are_not_rendered_as_hrefs(client, alice, django_user_model):
"""R2-S1 render boundary: even if a bad URL is already in the database
(stored before validation existed), it must not become a clickable
javascript: link."""
feed = Feed.objects.create(
feed_url="https://example.com/feed.xml", site_url="javascript:alert(1)"
)
Subscription.objects.create(user=alice, feed=feed)
article = Article.objects.create(
feed=feed, guid="g1", title="Hello", link="javascript:alert(2)"
)
client.login(username="alice", password="pw-alice-123")
detail = client.get(reverse("reader:article_detail", args=[article.pk])).content.decode()
assert "javascript:" not in detail
assert "Original" not in detail
article.link = "https://example.com/real"
article.save()
detail = client.get(reverse("reader:article_detail", args=[article.pk])).content.decode()
assert 'href="https://example.com/real"' in detail
django_user_model.objects.create_user("admin", password="pw-admin-123", is_staff=True)
client.login(username="admin", password="pw-admin-123")
Feed.objects.filter(pk=feed.pk).update(fetch_error_count=2, last_fetch_status="error")
dashboard = client.get(reverse("core:dashboard")).content.decode()
assert "javascript:" not in dashboard
+2 -1
View File
@@ -1,4 +1,5 @@
{% extends "base.html" %} {% extends "base.html" %}
{% load safe_urls %}
{% block title %}Dashboard — Evection{% endblock %} {% block title %}Dashboard — Evection{% endblock %}
{% block content %} {% block content %}
<h1>Dashboard</h1> <h1>Dashboard</h1>
@@ -27,7 +28,7 @@
<tbody> <tbody>
{% for feed in erroring_feeds %} {% for feed in erroring_feeds %}
<tr> <tr>
<td><a href="{{ feed.site_url|default:feed.feed_url }}">{{ feed.title|default:feed.feed_url }}</a></td> <td><a href="{{ feed.site_url|default:feed.feed_url|safe_http_url }}">{{ feed.title|default:feed.feed_url }}</a></td>
<td>{{ feed.subscriber_count }}</td> <td>{{ feed.subscriber_count }}</td>
<td>{{ feed.get_last_fetch_status_display }}</td> <td>{{ feed.get_last_fetch_status_display }}</td>
<td>{{ feed.fetch_error_count }}</td> <td>{{ feed.fetch_error_count }}</td>
+2 -2
View File
@@ -1,4 +1,4 @@
<div class="article-content-header"> {% load safe_urls %}<div class="article-content-header">
<h2 class="article-content-title">{{ article.title|default:"(untitled)" }}</h2> <h2 class="article-content-title">{{ article.title|default:"(untitled)" }}</h2>
<p class="article-meta"> <p class="article-meta">
{% if article.feed.favicon_url %}<img src="{{ article.feed.favicon_url }}" alt="" class="feed-favicon">{% endif %} {% if article.feed.favicon_url %}<img src="{{ article.feed.favicon_url }}" alt="" class="feed-favicon">{% endif %}
@@ -6,7 +6,7 @@
{# fetched_at stands in when the feed gave no publish date #} {# fetched_at stands in when the feed gave no publish date #}
&middot; <time datetime="{{ article.published_at|default:article.fetched_at|date:"c" }}" data-local-format="long">{{ article.published_at|default:article.fetched_at|date:"M j, Y H:i" }}</time> &middot; <time datetime="{{ article.published_at|default:article.fetched_at|date:"c" }}" data-local-format="long">{{ article.published_at|default:article.fetched_at|date:"M j, Y H:i" }}</time>
{% if article.author %} &middot; {{ article.author }}{% endif %} {% if article.author %} &middot; {{ article.author }}{% endif %}
{% if article.link %} &middot; <a href="{{ article.link }}" target="_blank" rel="noopener noreferrer">Original &#8599;</a>{% endif %} {% with safe_link=article.link|safe_http_url %}{% if safe_link %} &middot; <a href="{{ safe_link }}" target="_blank" rel="noopener noreferrer">Original &#8599;</a>{% endif %}{% endwith %}
</p> </p>
<div <div