Do not allow the about: URI scheme

[git.ikiwiki.info.git] / IkiWiki / Plugin / htmlscrubber.pm

diff --git a/IkiWiki/Plugin/htmlscrubber.pm b/IkiWiki/Plugin/htmlscrubber.pm
index bc613f92477ef55ef384f8a1bbf2887670c0e7a7..e02a8591ef2eac17d9d34eba4031bcdb7ce6b3ab 100644 (file)
--- a/IkiWiki/Plugin/htmlscrubber.pm
+++ b/IkiWiki/Plugin/htmlscrubber.pm
@@ -18,6 +18,27 @@ my $_scrubber;
 sub scrubber { #{{{
        return $_scrubber if defined $_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",
+               # Selected unofficial schemes
+               "aim", "callto", "cvs", "ed2k", "feed", "fish", "gg",
+               "irc", "ircs", "lastfm", "ldaps", "magnet", "mms",
+               "msnim", "notes", "rsync", "secondlife", "skype", "ssh",
+               "sftp", "sms", "steam", "webcal", "ymsgr",
+       );
+       # data is a special case. Allow data:image/*, but
+       # disallow data:text/javascript and everything else.
+       my $link=qr/^(?:$uri_schemes:|data:image\/|[^:]+$)/i;
+

        eval q{use HTML::Scrubber};
        error($@) if $@;
        # Lists based on http://feedparser.org/docs/html-sanitization.html
        eval q{use HTML::Scrubber};
        error($@) if $@;
        # Lists based on http://feedparser.org/docs/html-sanitization.html


@@ -35,23 +56,27 @@ sub scrubber { #{{{
                }],
                default => [undef, { (
                        map { $_ => 1 } qw{
                }],
                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
                                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
                                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
                                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
                                playcount controls 
                        } ),
                        "/" => 1, # emit proper <hr /> XHTML

-                       }],
+                       href => $link,
+                       src => $link,
+                       action => $link,
+                       poster => $link,
+               }],

        );
        return $_scrubber;
 } # }}}
        );
        return $_scrubber;
 } # }}}