loofah 2.25.1 → 2.25.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d07f9d310067f14d41ee4661fd3cd831de5af3d1c60bbfc949ba57219636ee9f
-  data.tar.gz: 0ea8df2bfb5396bcbcbec9b1ba3c7d1d0e852739be595efc4e27826226246eac
+  metadata.gz: 4a721138b6b152897d72edddfb80cdb0f35200c39a8f37a2024b503e6cfacc95
+  data.tar.gz: b342436a5a4e544b504d3e4234935ecd09dd87eddb55be893a1105cfd6a627f6
 SHA512:
-  metadata.gz: 0562da17634578281969ad6ebab59608ca78048d46a0ef298a5f767e32a0c66d11d74c1edd89a9710c80b2a27cc745af434890f8a79f055748e213642084f0c2
-  data.tar.gz: a39abf331334da243c9b608ab0a41fe5c08c0a41622433c86a3013a8aaaa204458afc7b99fe7d9042471f467433c6f4101f8f09adaddfb80fe091bf2541b6917
+  metadata.gz: e8ffd17d4b47d19bbff8070fcfe0d111530e7f146abc3501deaed1eb3198481f5ae16ee597e2a0d033eeea8bda27a038d1832c7237e24067a36e724e037e06a9
+  data.tar.gz: 71f741d1fbcf65fc137b25906c183cf767c091b203210e06d59dbb8e209c12274c77415b03406b021eb16dd149e2f9822f70124cec0947494f955d3fd1e458ee

data/CHANGELOG.md

@@ -1,5 +1,20 @@
 # Changelog
 
+## 2.25.2 / 2026-07-15
+
+### Security
+
+* Ensure `Loofah::HTML5::Scrub.allowed_uri?` recognizes numeric character references without semicolons (e.g. `javascript&#58alert(1)`), which browsers decode and execute, and rejects schemes split by them. See [GHSA-5qhf-9phg-95m2](https://github.com/flavorjones/loofah/security/advisories/GHSA-5qhf-9phg-95m2). @flavorjones
+* Ensure `Loofah::HTML5::Scrub.allowed_uri?` recognizes the named character references `	` and `
`, which `CGI.unescapeHTML` does not decode and browsers strip from URIs, and rejects schemes split by them (e.g. `java	script:alert(1)`). See [GHSA-8whx-365g-h9vv](https://github.com/flavorjones/loofah/security/advisories/GHSA-8whx-365g-h9vv). @flavorjones
+* Ensure that both `href` and `xlink:href` attributes on SVG elements like `use` are restricted to local (same-document) references. Previously only `xlink:href` was restricted, allowing the SVG 2 `href` attribute to reference external documents. See [GHSA-9wjq-cp2p-hrgf](https://github.com/flavorjones/loofah/security/advisories/GHSA-9wjq-cp2p-hrgf). @flavorjones
+
+### Improved
+
+* Harden `data:` URI mediatype parsing in `Loofah::HTML5::Scrub.allowed_uri?`. The mediatype is now parsed following the [WHATWG data: URL spec](https://fetch.spec.whatwg.org/#data-urls) and [RFC 2397](https://www.rfc-editor.org/rfc/rfc2397) instead of simply being split on a colon. A `data:` URI with an omitted or malformed mediatype is now treated as `text/plain` and allowed, and one without the required comma is now rejected. #305 @flavorjones
+* Remove `feed` from the default set of allowed protocols. The [feed URI scheme](https://en.wikipedia.org/wiki/Feed_URI_scheme) was never accepted as a standard protocol, and no major browser supports it. Removing it reduces the attack surface particularly for non-browser contexts. #304 @flavorjones
+* Remove a vestigial `&#x70` alternative from `Loofah::HTML5::SafeList::PROTOCOL_SEPARATOR`. This appears to be an ancient typo dating back to pre-extraction Rails circa 2007. #305 @flavorjones
+
+
 ## 2.25.1 / 2026-03-17
 
 * Ensure `Loofah::HTML5::Scrub.allowed_uri?` recognizes unescaped whitespace entities and rejects schemas containing them. See [GHSA-46fp-8f5p-pf2m](https://github.com/flavorjones/loofah/security/advisories/GHSA-46fp-8f5p-pf2m). #302 @flavorjones

data/lib/loofah/html5/safelist.rb

@@ -605,6 +605,11 @@ module Loofah
         "stroke",
       ])
 
+      SVG_HREF_ATTRIBUTES = Set.new([
+        "xlink:href",
+        "href",
+      ])
+
       SVG_ALLOW_LOCAL_HREF = Set.new([
         "altGlyph",
         "animate",
@@ -978,7 +983,7 @@ module Loofah
         "stroke-opacity",
       ])
 
-      PROTOCOL_SEPARATOR = /:|(&#0*58)|(&#x70)|(&#x0*3a)|(%|%)3A/i
+      PROTOCOL_SEPARATOR = /:|(&#0*58)|(&#x0*3a)|(%|%)3A/i
 
       ACCEPTABLE_PROTOCOLS = Set.new([
         "afs",
@@ -987,7 +992,6 @@ module Loofah
         "data",
         "ed2k",
         "fax",
-        "feed",
         "ftp",
         "gopher",
         "http",

data/lib/loofah/html5/scrub.rb

@@ -14,7 +14,43 @@ module Loofah
       CSS_WHITESPACE = " "
       CSS_PROPERTY_STRING_WITHOUT_EMBEDDED_QUOTES = /\A(["'])?[^"']+\1\z/
       DATA_ATTRIBUTE_NAME = /\Adata-[\w-]+\z/
-      URI_PROTOCOL_REGEX = /\A[a-z][a-z0-9+\-.]*:/ # RFC 3986
+
+      # Decimal (`&#58`) or hexadecimal (`&#x3a`) form, with or without the trailing semicolon that
+      # CGI.unescapeHTML requires but browsers do not.
+      NUMERIC_CHARACTER_REFERENCE = /&#(x[0-9a-f]+|[0-9]+);?/i
+
+      # A scheme (RFC 3986) followed by a protocol separator. The separator must recognize the same
+      # encoded-colon forms as PROTOCOL_SEPARATOR, otherwise a scheme split by an encoded colon (for
+      # example "javascript&#58alert(1)") would not be recognized as having a scheme and would skip
+      # protocol validation.
+      URI_PROTOCOL_REGEX = /\A[a-z][a-z0-9+\-.]*#{SafeList::PROTOCOL_SEPARATOR}/
+
+      # Matches a valid MIME type "essence" (type "/" subtype, no parameters), used to
+      # decide whether a data: URI mediatype is well-formed; a non-match is not a valid
+      # MIME type, which the data: URL processor treats as text/plain. Specs:
+      #
+      #   https://mimesniff.spec.whatwg.org/#valid-mime-type
+      #   https://mimesniff.spec.whatwg.org/#mime-type-essence
+      #   https://mimesniff.spec.whatwg.org/#http-token-code-point
+      #
+      # The character class below is the HTTP token set (tchar) from RFC 9110 section
+      # 5.6.2, https://www.rfc-editor.org/rfc/rfc9110#name-tokens :
+      #
+      #   tchar = "!" / "#" / "$" / "%" / "&" / "'" / "*" / "+" / "-" / "." / "^"
+      #         / "_" / "`" / "|" / "~" / DIGIT / ALPHA
+      #
+      # ALPHA is written a-z, not a-zA-Z, because allowed_uri? downcases the input first.
+      DATA_URI_MEDIATYPE = %r{
+        \A
+        [a-z0-9!\#$%&'*+\-.^_`|~]+   # type:    1*tchar
+        /                            # "/" is not a tchar, so it is the sole delimiter
+        [a-z0-9!\#$%&'*+\-.^_`|~]+   # subtype: 1*tchar
+        \z
+      }x
+
+      # HTML5 named character references for whitespace that browsers strip from
+      # URIs. CGI.unescapeHTML does not decode these, so they are handled explicitly.
+      WHITESPACE_CHARACTER_REFERENCES = /&(Tab|NewLine);/
 
       class << self
         def allowed_element?(element_name)
@@ -48,7 +84,7 @@ module Loofah
             end
 
             next unless SafeList::SVG_ALLOW_LOCAL_HREF.include?(node.name) &&
-              attr_name == "xlink:href" &&
+              SafeList::SVG_HREF_ATTRIBUTES.include?(attr_name) &&
               attr_node.value =~ /^\s*[^#\s].*/m
 
             attr_node.remove
@@ -141,29 +177,52 @@ module Loofah
           attr_node.value = values.join(" ")
         end
 
-        # Returns true if the given URI string is safe, false otherwise.
-        # This method can be used to validate URI attribute values without
-        # requiring a Nokogiri DOM node.
+        # Returns true if the given URI string is safe, false otherwise. This method can be used to
+        # validate URI attribute values without requiring a Nokogiri DOM node.
         def allowed_uri?(uri_string)
-          # Replace control characters both before and after unescaping.
-          uri_string = CGI.unescapeHTML(uri_string.gsub(CONTROL_CHARACTERS, ""))
-            .gsub(CONTROL_CHARACTERS, "")
-            .gsub("&colon;", ":")
-            .downcase
+          # CGI.unescapeHTML decodes numeric references only when they carry a trailing semicolon, so
+          # also decode the semicolon-less ones, which browsers still decode and execute. Normalizing
+          # more aggressively than a browser only rejects more, which is safe. Control characters are
+          # stripped both before and after decoding, since decoding can produce them. That strip must
+          # precede WHITESPACE_CHARACTER_REFERENCES: removing a control character can reveal a named
+          # whitespace reference.
+          uri_string = decode_numeric_character_references(CGI.unescapeHTML(uri_string.gsub(CONTROL_CHARACTERS, "")))
+          uri_string.gsub!(CONTROL_CHARACTERS, "")
+          uri_string.gsub!(WHITESPACE_CHARACTER_REFERENCES, "")
+          uri_string.gsub!("&colon;", ":")
+          uri_string.downcase!
           if URI_PROTOCOL_REGEX.match?(uri_string)
             protocol = uri_string.split(SafeList::PROTOCOL_SEPARATOR)[0]
             return false unless SafeList::ALLOWED_PROTOCOLS.include?(protocol)
 
             if protocol == "data"
               # permit only allowed data mediatypes
-              mediatype = uri_string.split(SafeList::PROTOCOL_SEPARATOR)[1]
-              mediatype, _ = mediatype.split(/[;,]/)[0..1] if mediatype
-              return false if mediatype && !SafeList::ALLOWED_URI_DATA_MEDIATYPES.include?(mediatype)
+              return false unless SafeList::ALLOWED_URI_DATA_MEDIATYPES.include?(data_uri_mediatype(uri_string))
             end
           end
           true
         end
 
+        def decode_numeric_character_references(string)
+          string.gsub(NUMERIC_CHARACTER_REFERENCE) do |reference|
+            digits = ::Regexp.last_match(1)
+            hexadecimal = digits.start_with?("x", "X")
+            digits = digits[1..-1] if hexadecimal
+            significant_digits = digits.sub(/\A0+/, "")
+
+            # The largest code point is U+10FFFF: 7 decimal or 6 hexadecimal significant digits.
+            # Anything longer is out of range; skip it without building a large integer from it.
+            next reference if significant_digits.length > (hexadecimal ? 6 : 7)
+
+            codepoint = significant_digits.to_i(hexadecimal ? 16 : 10)
+            begin
+              codepoint.chr(Encoding::UTF_8)
+            rescue RangeError
+              reference
+            end
+          end
+        end
+
         def scrub_uri_attribute(attr_node)
           if allowed_uri?(attr_node.value)
             false
@@ -238,6 +297,20 @@ module Loofah
             string
           end
         end
+
+        private
+
+        # Returns the mediatype of a data: URI per RFC 2397, or nil when the
+        # required comma is absent. allowed_uri? entity-decodes, downcases, and
+        # strips control characters before calling this. An omitted or malformed
+        # mediatype resolves to "text/plain", matching the WHATWG data: URL processor.
+        def data_uri_mediatype(uri_string)
+          metadata, comma, _data = uri_string.delete_prefix("data:").partition(",")
+          return nil if comma.empty?
+
+          mediatype = metadata.delete_suffix(";base64").split(";", 2).first.to_s.strip
+          mediatype.match?(DATA_URI_MEDIATYPE) ? mediatype : "text/plain"
+        end
       end
     end
   end

data/lib/loofah/version.rb

@@ -2,5 +2,5 @@
 
 module Loofah
   # The version of Loofah you are using
-  VERSION = "2.25.1"
+  VERSION = "2.25.2"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: loofah
 version: !ruby/object:Gem::Version
-  version: 2.25.1
+  version: 2.25.2
 platform: ruby
 authors:
 - Mike Dalessio
@@ -96,7 +96,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 4.0.3
+rubygems_version: 4.0.10
 specification_version: 4
 summary: Loofah is a general library for manipulating and transforming HTML/XML documents
   and fragments, built on top of Nokogiri.