* htmlscrubber security fix: Block javascript in uris.

* Add htmlscrubber test suite.

diff --git a/IkiWiki/Plugin/htmlscrubber.pm b/IkiWiki/Plugin/htmlscrubber.pm
index bc613f92477ef55ef384f8a1bbf2887670c0e7a7..25caa8a506cdf5ab8ea0c9b0d3e9e935f62bd6f8 100644 (file)
--- a/IkiWiki/Plugin/htmlscrubber.pm
+++ b/IkiWiki/Plugin/htmlscrubber.pm
@@ -18,6 +18,28 @@ my $_scrubber;
 sub scrubber { #{{{
        return $_scrubber if defined $_scrubber;
        
+       # Only known uri schemes are allowed to avoid all the ways of
+       # embedding javascrpt.
+       # List at http://en.wikipedia.org/wiki/URI_scheme
+       my $uri_schemes=join("|",
+               # IANA registered schemes
+               "http", "https", "ftp", "mailto", "file", "telnet", "gopher",
+               "aaa", "aaas", "acap",  "cap", "cid", "crid", 
+               "dav", "dict", "dns", "fax", "go", "h323", "im", "imap",
+               "ldap", "mid", "news", "nfs", "nntp", "pop", "pres",
+               "sip", "sips", "snmp", "tel", "urn", "wais", "xmpp",
+               "z39.50r", "z39.50s",
+               # data is a special case. Allow data:text/<image>, but
+               # disallow data:text/javascript and everything else.
+               qr/data:text\/(?:png|gif|jpeg)/,
+               # Selected unofficial schemes
+               "about", "aim", "callto", "cvs", "ed2k", "feed", "fish", "gg",
+               "irc", "ircs", "lastfm", "ldaps", "magnet", "mms",
+               "msnim", "notes", "rsync", "secondlife", "skype", "ssh",
+               "sftp", "sms", "steam", "webcal", "ymsgr",
+       );
+       my $link=qr/^(?:$uri_schemes:|[^:]+$)/i;
+
        eval q{use HTML::Scrubber};
        error($@) if $@;
        # Lists based on http://feedparser.org/docs/html-sanitization.html
@@ -35,23 +57,27 @@ sub scrubber { #{{{
                }],
                default => [undef, { (
                        map { $_ => 1 } qw{
-                               abbr accept accept-charset accesskey action
+                               abbr accept accept-charset accesskey
                                align alt axis border cellpadding cellspacing
                                char charoff charset checked cite class
                                clear cols colspan color compact coords
                                datetime dir disabled enctype for frame
-                               headers height href hreflang hspace id ismap
+                               headers height hreflang hspace id ismap
                                label lang longdesc maxlength media method
                                multiple name nohref noshade nowrap prompt
                                readonly rel rev rows rowspan rules scope
-                               selected shape size span src start summary
+                               selected shape size span start summary
                                tabindex target title type usemap valign
                                value vspace width
-                               poster autoplay loopstart loopend end
+                               autoplay loopstart loopend end
                                playcount controls 
                        } ),
                        "/" => 1, # emit proper <hr /> XHTML
-                       }],
+                       href => $link,
+                       src => $link,
+                       action => $link,
+                       poster => $link,
+               }],
        );
        return $_scrubber;
 } # }}}

diff --git a/debian/changelog b/debian/changelog
index 420cef5ad9e0e3a440936f756b4b78c9fc693fdd..fb8d6bc5b01d2c5429c10c7213d7b375546c5770 100644 (file)
--- a/debian/changelog
+++ b/debian/changelog
@@ -8,6 +8,10 @@ ikiwiki (2.40) UNRELEASED; urgency=low
     the underlay to support either setting of prefix_directives.  Add NEWS
     entry with migration information.
 
+  [ Joey Hess ]
+  * htmlscrubber security fix: Block javascript in uris.
+  * Add htmlscrubber test suite.
+
  -- Josh Triplett <josh@freedesktop.org>  Sat, 09 Feb 2008 23:01:19 -0800
 
 ikiwiki (2.31) unstable; urgency=low

diff --git a/doc/plugins/htmlscrubber.mdwn b/doc/plugins/htmlscrubber.mdwn
index 6ce297a86bbc48ddda36dc6b51eb8ada39566312..d7bcf8099e00e3dd116bddd60ab67c8082639f1f 100644 (file)
--- a/doc/plugins/htmlscrubber.mdwn
+++ b/doc/plugins/htmlscrubber.mdwn
@@ -36,3 +36,4 @@ plugin is active:
 * <span style="background: url(javascript:window.location='http://example.org/')">CSS script test</span>
 * <span style="&#x61;&#x6e;&#x79;&#x3a;&#x20;&#x65;&#x78;&#x70;&#x72;&#x65;&#x73;&#x73;&#x69;&#x6f;&#x6e;&#x28;&#x77;&#x69;&#x6e;&#x64;&#x6f;&#x77;&#x2e;&#x6c;&#x6f;&#x63;&#x61;&#x74;&#x69;&#x6f;&#x6e;&#x3d;&#x27;&#x68;&#x74;&#x74;&#x70;&#x3a;&#x2f;&#x2f;&#x65;&#x78;&#x61;&#x6d;&#x70;&#x6c;&#x65;&#x2e;&#x6f;&#x72;&#x67;&#x2f;&#x27;&#x29;">entity-encoded CSS script test</span>
 * <span style="&#97;&#110;&#121;&#58;&#32;&#101;&#120;&#112;&#114;&#101;&#115;&#115;&#105;&#111;&#110;&#40;&#119;&#105;&#110;&#100;&#111;&#119;&#46;&#108;&#111;&#99;&#97;&#116;&#105;&#111;&#110;&#61;&#39;&#104;&#116;&#116;&#112;&#58;&#47;&#47;&#101;&#120;&#97;&#109;&#112;&#108;&#101;&#46;&#111;&#114;&#103;&#47;&#39;&#41;">entity-encoded CSS script test</span>
+* <a href="javascript&#x3A;alert('foo')">click me</a>

diff --git a/t/htmlize.t b/t/htmlize.t
index 9e2e3ec594eded64c1b9388c705db515583b89e1..edf357010a0b551b58f895908cfd1858bc9e5f95 100755 (executable)
--- a/t/htmlize.t
+++ b/t/htmlize.t
@@ -1,7 +1,7 @@
 #!/usr/bin/perl
 use warnings;
 use strict;
-use Test::More tests => 16;
+use Test::More tests => 26;
 use Encode;
 
 BEGIN { use_ok("IkiWiki"); }
@@ -20,7 +20,6 @@ is(IkiWiki::htmlize("foo", "mdwn", readfile("t/test1.mdwn")),
 ok(IkiWiki::htmlize("foo", "mdwn", readfile("t/test2.mdwn")),
        "this file crashes markdown if it's fed in as decoded utf-8");
 
-# embedded javascript sanitisation tests
 sub gotcha {
        my $html=IkiWiki::htmlize("foo", "mdwn", shift);
        return $html =~ /GOTCHA/;
@@ -41,10 +40,31 @@ ok(!gotcha(q{<span style="&#97;&#110;&#121;&#58;&#32;&#101;&#120;&#112;&#114;&#1
        "another entity-encoded CSS script test");
 ok(!gotcha(q{<script>GOTCHA</script>}),
        "script tag");
+ok(!gotcha(q{<form action="javascript:alert('GOTCHA')">foo</form>}),
+       "form action with javascript");
+ok(!gotcha(q{<video poster="javascript:alert('GOTCHA')" href="foo.avi">foo</video>}),
+       "video poster with javascript");
 ok(!gotcha(q{<span style="background: url(javascript:window.location=GOTCHA)">a</span>}),
        "CSS script test");
+ok(! gotcha(q{<img src="data:text/javascript:GOTCHA">}),
+       "data:text/javascript (jeez!)");
+ok(gotcha(q{<img src="data:text/png:GOTCHA">}), "data:text/png");
+ok(gotcha(q{<img src="data:text/gif:GOTCHA">}), "data:text/gif");
+ok(gotcha(q{<img src="data:text/jpeg:GOTCHA">}), "data:text/jpeg");
 ok(gotcha(q{<p>javascript:alert('GOTCHA')</p>}),
        "not javascript AFAIK (but perhaps some web browser would like to
        be perverse and assume it is?)");
 ok(gotcha(q{<img src="javascript.png?GOTCHA">}), "not javascript");
 ok(gotcha(q{<a href="javascript.png?GOTCHA">foo</a>}), "not javascript");
+is(IkiWiki::htmlize("foo", "mdwn",
+       q{<img alt="foo" src="foo.gif">}),
+       q{<img alt="foo" src="foo.gif">}, "img with alt tag allowed");
+is(IkiWiki::htmlize("foo", "mdwn",
+       q{<a href="http://google.com/">}),
+       q{<a href="http://google.com/">}, "absolute url allowed");
+is(IkiWiki::htmlize("foo", "mdwn",
+       q{<a href="foo.html">}),
+       q{<a href="foo.html">}, "relative url allowed");
+is(IkiWiki::htmlize("foo", "mdwn",
+       q{<span class="foo">bar</span>}),
+       q{<span class="foo">bar</span>}, "class attribute allowed");