Mercurial > kallithea
changeset 7544:2ac4499b25eb
lib: sanitize HTML for all types of README rendering, not only markdown
The repository summary page will display a rendered version of the
repository 'readme' based on its file extension. In commit 5746cc3b3fa5,
the rendered output was already sanitized when the input was markdown.
However, also readmes written in other formats, like ReStructuredText (RST)
or plain text could have content that we want sanitized.
Therefore, move the sanitizing one level up so it covers all renderers, for
now and the future.
This fixes an XSS issue when a repository readme contains javascript code,
which would be executed when the repository summary page is visited by a
user.
Reported by Bob Hogg <wombat@rwhogg.site> (thanks!).
| author | Thomas De Schampheleire <thomas.de_schampheleire@nokia.com> |
|---|---|
| date | Sat, 26 Jan 2019 20:27:50 +0100 |
| parents | c9159e6fda04 |
| children | 109b068ba6e5 |
| files | kallithea/lib/markup_renderer.py |
| diffstat | 1 files changed, 17 insertions(+), 17 deletions(-) [+] |
line wrap: on
line diff
--- a/kallithea/lib/markup_renderer.py Sat Jan 26 20:00:14 2019 +0100 +++ b/kallithea/lib/markup_renderer.py Sat Jan 26 20:27:50 2019 +0100 @@ -124,7 +124,19 @@ renderer = self._detect_renderer(source, filename) readme_data = renderer(source) - return readme_data + # Allow most HTML, while preventing XSS issues: + # no <script> tags, no onclick attributes, no javascript + # "protocol", and also limit styling to prevent defacing. + return bleach.clean(readme_data, + tags=['a', 'abbr', 'b', 'blockquote', 'br', 'code', 'dd', + 'div', 'dl', 'dt', 'em', 'h1', 'h2', 'h3', 'h4', 'h5', + 'h6', 'hr', 'i', 'img', 'li', 'ol', 'p', 'pre', 'span', + 'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'th', + 'thead', 'tr', 'ul'], + attributes=['class', 'id', 'style', 'label', 'title', 'alt', 'href', 'src'], + styles=['color'], + protocols=['http', 'https', 'mailto'], + ) @classmethod def plain(cls, source, universal_newline=True): @@ -162,22 +174,10 @@ try: if flavored: source = cls._flavored_markdown(source) - markdown_html = markdown_mod.markdown(source, - extensions=['codehilite', 'extra'], - extension_configs={'codehilite': {'css_class': 'code-highlight'}}) - # Allow most HTML, while preventing XSS issues: - # no <script> tags, no onclick attributes, no javascript - # "protocol", and also limit styling to prevent defacing. - return bleach.clean(markdown_html, - tags=['a', 'abbr', 'b', 'blockquote', 'br', 'code', 'dd', - 'div', 'dl', 'dt', 'em', 'h1', 'h2', 'h3', 'h4', 'h5', - 'h6', 'hr', 'i', 'img', 'li', 'ol', 'p', 'pre', 'span', - 'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'th', - 'thead', 'tr', 'ul'], - attributes=['class', 'id', 'style', 'label', 'title', 'alt', 'href', 'src'], - styles=['color'], - protocols=['http', 'https', 'mailto'], - ) + return markdown_mod.markdown( + source, + extensions=['codehilite', 'extra'], + extension_configs={'codehilite': {'css_class': 'code-highlight'}}) except Exception: log.error(traceback.format_exc()) if safe: