markup/goldmark: Sanitize TOC heading titles

Fixes #13401

diff --git a/go.mod b/go.mod
index 4de91dd5dd9907b475f5c56e9612337ebacdd4a1..a745e4c5760e106f90c6816a03d6c9e75af7c32e 100644 (file)
--- a/go.mod
+++ b/go.mod
@@ -123,6 +123,7 @@ require (
        github.com/aws/aws-sdk-go-v2/service/ssooidc v1.26.4 // indirect
        github.com/aws/aws-sdk-go-v2/service/sts v1.30.3 // indirect
        github.com/aws/smithy-go v1.22.2 // indirect
+       github.com/aymerick/douceur v0.2.0 // indirect
        github.com/cncf/xds/go v0.0.0-20250326154945-ae57f3c0d45f // indirect
        github.com/cpuguy83/go-md2man/v2 v2.0.6 // indirect
        github.com/dlclark/regexp2 v1.11.5 // indirect
@@ -141,6 +142,7 @@ require (
        github.com/google/wire v0.6.0 // indirect
        github.com/googleapis/enterprise-certificate-proxy v0.3.6 // indirect
        github.com/googleapis/gax-go/v2 v2.14.2 // indirect
+       github.com/gorilla/css v1.0.1 // indirect
        github.com/hashicorp/golang-lru/v2 v2.0.7 // indirect
        github.com/inconshreveable/mousetrap v1.1.0 // indirect
        github.com/jmespath/go-jmespath v0.4.0 // indirect
@@ -151,6 +153,7 @@ require (
        github.com/mailru/easyjson v0.7.7 // indirect
        github.com/mattn/go-colorable v0.1.13 // indirect
        github.com/mattn/go-runewidth v0.0.16 // indirect
+       github.com/microcosm-cc/bluemonday v1.0.27 // indirect
        github.com/mohae/deepcopy v0.0.0-20170929034955-c48cc78d4826 // indirect
        github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646 // indirect
        github.com/oasdiff/yaml v0.0.0-20250309154309-f31be36b4037 // indirect

diff --git a/go.sum b/go.sum
index 0168642e8cedeb3e2975625a9df23b76e7bd978e..76c5702e3245786f0e2668b1f11c515b890815d1 100644 (file)
--- a/go.sum
+++ b/go.sum
@@ -137,6 +137,8 @@ github.com/aws/aws-sdk-go-v2/service/sts v1.30.3 h1:ZsDKRLXGWHk8WdtyYMoGNO7bTudr
 github.com/aws/aws-sdk-go-v2/service/sts v1.30.3/go.mod h1:zwySh8fpFyXp9yOr/KVzxOl8SRqgf/IDw5aUt9UKFcQ=
 github.com/aws/smithy-go v1.22.2 h1:6D9hW43xKFrRx/tXXfAlIZc4JI+yQe6snnWcQyxSyLQ=
 github.com/aws/smithy-go v1.22.2/go.mod h1:irrKGvNn1InZwb2d7fkIRNucdfwR8R+Ts3wxYa/cJHg=
+github.com/aymerick/douceur v0.2.0 h1:Mv+mAeH1Q+n9Fr+oyamOlAkUNPWPlA8PPGR0QAaYuPk=
+github.com/aymerick/douceur v0.2.0/go.mod h1:wlT5vV2O3h55X9m7iVYN0TBM0NH/MmbLnd30/FjWUq4=
 github.com/bep/clocks v0.5.0 h1:hhvKVGLPQWRVsBP/UB7ErrHYIO42gINVbvqxvYTPVps=
 github.com/bep/clocks v0.5.0/go.mod h1:SUq3q+OOq41y2lRQqH5fsOoxN8GbxSiT6jvoVVLCVhU=
 github.com/bep/debounce v1.2.0 h1:wXds8Kq8qRfwAOpAxHrJDbCXgC5aHSzgQb/0gKsHQqo=
@@ -352,6 +354,8 @@ github.com/googleapis/gax-go/v2 v2.0.5/go.mod h1:DWXyrwAJ9X0FpwwEdw+IPEYBICEFu5m
 github.com/googleapis/gax-go/v2 v2.14.2 h1:eBLnkZ9635krYIPD+ag1USrOAI0Nr0QYF3+/3GqO0k0=
 github.com/googleapis/gax-go/v2 v2.14.2/go.mod h1:ON64QhlJkhVtSqp4v1uaK92VyZ2gmvDQsweuyLV+8+w=
 github.com/googleapis/google-cloud-go-testing v0.0.0-20200911160855-bcd43fbb19e8/go.mod h1:dvDLG8qkwmyD9a/MJJN3XJcT3xFxOKAvTZGvuZmac9g=
+github.com/gorilla/css v1.0.1 h1:ntNaBIghp6JmvWnxbZKANoLyuXTPZ4cAMlo6RyhlbO8=
+github.com/gorilla/css v1.0.1/go.mod h1:BvnYkspnSzMmwRK+b8/xgNPLiIuNZr6vbZBTPQ2A3b0=
 github.com/gorilla/websocket v1.5.3 h1:saDtZ6Pbx/0u+bgYQ3q96pZgCzfhKXGPqt7kZ72aNNg=
 github.com/gorilla/websocket v1.5.3/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
 github.com/hairyhenderson/go-codeowners v0.7.0 h1:s0W4wF8bdsBEjTWzwzSlsatSthWtTAF2xLgo4a4RwAo=
@@ -406,6 +410,8 @@ github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWE
 github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
 github.com/mattn/go-runewidth v0.0.16 h1:E5ScNMtiwvlvB5paMFdw9p4kSQzbXFikJ5SQO6TULQc=
 github.com/mattn/go-runewidth v0.0.16/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w=
+github.com/microcosm-cc/bluemonday v1.0.27 h1:MpEUotklkwCSLeH+Qdx1VJgNqLlpY2KXwXFM08ygZfk=
+github.com/microcosm-cc/bluemonday v1.0.27/go.mod h1:jFi9vgW+H7c3V0lb6nR74Ib/DIB5OBs92Dimizgw2cA=
 github.com/mitchellh/mapstructure v1.5.1-0.20231216201459-8508981c8b6c h1:cqn374mizHuIWj+OSJCajGr/phAmuMug9qIX3l9CflE=
 github.com/mitchellh/mapstructure v1.5.1-0.20231216201459-8508981c8b6c/go.mod h1:bFUtVrKA4DC2yAKiSyO/QUcy7e+RRV2QTWOzhPopBRo=
 github.com/mohae/deepcopy v0.0.0-20170929034955-c48cc78d4826 h1:RWengNIwukTxcDr9M+97sNutRR1RKhG96O6jWumTTnw=

diff --git a/markup/goldmark/toc.go b/markup/goldmark/toc.go
index 538f65df45237a05e389f9d8f2c87169b8a97911..b4dcc425fa4b366acfbdec25c680a8cce8fb7a55 100644 (file)
--- a/markup/goldmark/toc.go
+++ b/markup/goldmark/toc.go
@@ -15,7 +15,10 @@ package goldmark
 
 import (
        "bytes"
+       "regexp"
+       "strings"
 
+       "github.com/microcosm-cc/bluemonday"
        strikethroughAst "github.com/yuin/goldmark/extension/ast"
 
        emojiAst "github.com/yuin/goldmark-emoji/ast"
@@ -61,7 +64,7 @@ func (t *tocTransformer) Transform(n *ast.Document, reader text.Reader, pc parse
                s := ast.WalkStatus(ast.WalkContinue)
                if n.Kind() == ast.KindHeading {
                        if inHeading && !entering {
-                               tocHeading.Title = headingText.String()
+                               tocHeading.Title = sanitizeTOCHeadingTitle(headingText.String())
                                headingText.Reset()
                                toc.AddAt(tocHeading, row, level-1)
                                tocHeading = &tableofcontents.Heading{}
@@ -139,3 +142,40 @@ func (e *tocExtension) Extend(m goldmark.Markdown) {
                // This must run after the ID generation (priority 100).
                110)))
 }
+
+var tocSanitizerPolicy = newTOCSanitizerPolicy()
+
+// newTOCSanitizerPolicy returns a bluemonday policy for sanitizing TOC heading
+// titles against an allowlist of inline HTML elements and attributes,
+// specifically excluding anchor elements to prevent links within TOC heading
+// titles.
+func newTOCSanitizerPolicy() *bluemonday.Policy {
+       p := bluemonday.NewPolicy()
+       p.AllowElements(
+               "abbr", "b", "bdi", "bdo", "br", "cite", "code", "data", "del", "dfn",
+               "em", "i", "ins", "kbd", "mark", "q", "rp", "rt", "ruby", "s", "samp",
+               "small", "span", "strong", "sub", "sup", "time", "u", "var", "wbr",
+       )
+       p.AllowStandardAttributes()
+       p.AllowStyling()
+       p.AllowImages()
+       p.AllowAttrs("cite").OnElements("del", "ins", "q")
+       p.AllowAttrs("datetime").OnElements("del", "ins", "time")
+       p.AllowAttrs("value").OnElements("data")
+       return p
+}
+
+var whiteSpaceRe = regexp.MustCompile(`\s+`)
+
+// sanitizeTOCHeadingTitle sanitizes s for use as a TOC heading title.
+func sanitizeTOCHeadingTitle(s string) string {
+       if strings.IndexByte(s, '<') == -1 {
+               return s
+       }
+
+       // Sanitize the string.
+       ss := tocSanitizerPolicy.Sanitize(s)
+
+       // Remove extraneous whitespace.
+       return whiteSpaceRe.ReplaceAllString(strings.TrimSpace(ss), " ")
+}

diff --git a/markup/goldmark/toc_integration_test.go b/markup/goldmark/toc_integration_test.go
index 814ae199b3426d18be7be290075b114d3a05a228..b4dfeee05228981a1232c98b66e2e05d694fb97e 100644 (file)
--- a/markup/goldmark/toc_integration_test.go
+++ b/markup/goldmark/toc_integration_test.go
@@ -90,6 +90,11 @@ title: p6 (strikethrough)
 title: p7 (emoji)
 ---
 ## A :snake: emoji
+-- content/p8.md --
+---
+title: p8 (link)
+---
+## A [link](https://example.org)
 `
 
        b := hugolib.Test(t, files)
@@ -111,36 +116,41 @@ title: p7 (emoji)
 </nav>`)
 
        // markdown
-       b.AssertFileContent("public/p2/index.html", `<nav id="TableOfContents">
-<li><a href="#">Some <em>emphasized</em> text</a></li>
-<li><a href="#">Some <code>inline</code> code</a></li>
-<li><a href="#">Something to escape A &lt; B &amp;&amp; C &gt; B</a></li>
-`)
+       b.AssertFileContent("public/p2/index.html",
+               `<li><a href="#">Some <em>emphasized</em> text</a></li>`,
+               `<li><a href="#">Some <code>inline</code> code</a></li>`,
+               `<li><a href="#">Something to escape A &lt; B &amp;&amp; C &gt; B</a></li>`,
+       )
 
        // image
-       b.AssertFileContent("public/p3/index.html", `
-<li><a href="#">An image <img src="a.jpg" alt="kitten"></a></li>
-`)
+       b.AssertFileContent("public/p3/index.html",
+               `<li><a href="#">An image <img src="a.jpg" alt="kitten"></a></li>`,
+       )
 
        // raw html
-       b.AssertFileContent("public/p4/index.html", `
-<li><a href="#">Some <!-- raw HTML omitted -->raw<!-- raw HTML omitted --> HTML</a></li>
-`)
+       b.AssertFileContent("public/p4/index.html",
+               `<li><a href="#">Some raw HTML</a></li>`,
+       )
 
        // typographer
-       b.AssertFileContent("public/p5/index.html", `
-<li><a href="#">Some &quot;typographer&quot; markup</a></li>
-`)
+       b.AssertFileContent("public/p5/index.html",
+               `<li><a href="#">Some &quot;typographer&quot; markup</a></li>`,
+       )
 
        // strikethrough
-       b.AssertFileContent("public/p6/index.html", `
-<li><a href="#">Some ~~deleted~~ text</a></li>
-       `)
+       b.AssertFileContent("public/p6/index.html",
+               `<li><a href="#">Some ~~deleted~~ text</a></li>`,
+       )
 
        // emoji
-       b.AssertFileContent("public/p7/index.html", `
-<li><a href="#">A :snake: emoji</a></li>
-               `)
+       b.AssertFileContent("public/p7/index.html",
+               `<li><a href="#">A :snake: emoji</a></li>`,
+       )
+
+       // link
+       b.AssertFileContent("public/p8/index.html",
+               `<li><a href="#">A link</a></li>`,
+       )
 }
 
 func TestTableOfContentsAdvanced(t *testing.T) {
@@ -214,6 +224,11 @@ title: p6 (strikethrough)
 title: p7 (emoji)
 ---
 ## A :snake: emoji
+-- content/p8.md --
+---
+title: p8 (link)
+---
+## A [link](https://example.org)
 `
 
        b := hugolib.Test(t, files)
@@ -231,37 +246,41 @@ title: p7 (emoji)
 </nav>`)
 
        // markdown
-       b.AssertFileContent("public/p2/index.html", `<nav id="TableOfContents">
-<li><a href="#some-emphasized-text">Some <em>emphasized</em> text</a></li>
-<li><a href="#some-inline-code">Some <code>inline</code> code</a></li>
-<li><a href="#something-to-escape-a--b--c--b">Something to escape A &lt; B &amp;&amp; C &gt; B</a></li>
-`)
+       b.AssertFileContent("public/p2/index.html",
+               `<li><a href="#some-emphasized-text">Some <em>emphasized</em> text</a></li>`,
+               `<li><a href="#some-inline-code">Some <code>inline</code> code</a></li>`,
+               `<li><a href="#something-to-escape-a--b--c--b">Something to escape A &lt; B &amp;&amp; C &gt; B</a></li>`,
+       )
 
        // image
-       b.AssertFileContent("public/p3/index.html", `
-<li><a href="#an-image-kitten">An image <img src="a.jpg" alt="kitten" /></a></li>
-`)
+       b.AssertFileContent("public/p3/index.html",
+               `<li><a href="#an-image-kitten">An image <img src="a.jpg" alt="kitten"/></a></li>`,
+       )
 
        // raw html
-       b.AssertFileContent("public/p4/index.html", `
-<li><a href="#some-raw-html">Some <span>raw</span> HTML</a></li>
-`)
+       b.AssertFileContent("public/p4/index.html",
+               `<li><a href="#some-raw-html">Some <span>raw</span> HTML</a></li>`,
+       )
 
        // typographer
-       b.AssertFileContent("public/p5/index.html", `
-<li><a href="#some-typographer-markup">Some &ldquo;typographer&rdquo; markup</a></li>
-`)
+       b.AssertFileContent("public/p5/index.html",
+               `<li><a href="#some-typographer-markup">Some &ldquo;typographer&rdquo; markup</a></li>`,
+       )
 
        // strikethrough
-       b.AssertFileContent("public/p6/index.html", `
-<li><a href="#some-deleted-text">Some <del>deleted</del> text</a></li>
-`)
+       b.AssertFileContent("public/p6/index.html",
+               `<li><a href="#some-deleted-text">Some <del>deleted</del> text</a></li>`,
+       )
 
        // emoji
-
-       b.AssertFileContent("public/p7/index.html", `
-<li><a href="#a-snake-emoji">A &#x1f40d; emoji</a></li>
-`)
+       b.AssertFileContent("public/p7/index.html",
+               `<li><a href="#a-snake-emoji">A &#x1f40d; emoji</a></li>`,
+       )
+
+       // link
+       b.AssertFileContent("public/p8/index.html",
+               `<li><a href="#a-link">A link</a></li>`,
+       )
 }
 
 func TestIssue13416(t *testing.T) {