🔒 FIX: escape user content in renderers and harden attrs default

mdit_py_plugins/attrs/index.py

@@ -2,6 +2,7 @@
 
 from collections.abc import Sequence
 from functools import partial
+import re
 from typing import Any
 
 from markdown_it import MarkdownIt
@@ -56,10 +57,24 @@ def attrs_plugin(
     :param allowed: A list of allowed attribute names.
         If not ``None``, any attributes not in this list will be removed
         and placed in the token's meta under the key "insecure_attrs".
+        If ``None`` (the default), event-handler attributes
+        (any name starting with ``on``, such as ``onclick``) are still removed,
+        as a baseline protection against script injection.
+        Other attributes, including ``style``, are kept.
+        Whatever ``allowed`` says, the URL-valued attributes
+        ``href``, ``src``, ``action``, ``formaction`` and ``xlink:href``
+        are removed when ``md.validateLink`` rejects their value
+        (for example a ``javascript:`` URL), as for Markdown links and images.
+        This is not a full sanitiser: to safely render untrusted input,
+        pass an explicit ``allowed`` list (e.g. ``("id", "class")``).
     """
 
     if spans:
-        md.inline.ruler.after(span_after, "span", _span_rule)
+        md.inline.ruler.after(
+            span_after,
+            "span",
+            partial(_span_rule, allowed=None if allowed is None else set(allowed)),
+        )
     if after:
         md.inline.ruler.push(
             "attr",
@@ -91,6 +106,16 @@ def attrs_block_plugin(md: MarkdownIt, *, allowed: Sequence[str] | None = None)
     :param allowed: A list of allowed attribute names.
         If not ``None``, any attributes not in this list will be removed
         and placed in the token's meta under the key "insecure_attrs".
+        If ``None`` (the default), event-handler attributes
+        (any name starting with ``on``, such as ``onclick``) are still removed,
+        as a baseline protection against script injection.
+        Other attributes, including ``style``, are kept.
+        Whatever ``allowed`` says, the URL-valued attributes
+        ``href``, ``src``, ``action``, ``formaction`` and ``xlink:href``
+        are removed when ``md.validateLink`` rejects their value
+        (for example a ``javascript:`` URL), as for Markdown links and images.
+        This is not a full sanitiser: to safely render untrusted input,
+        pass an explicit ``allowed`` list (e.g. ``("id", "class")``).
     """
     md.block.ruler.before("fence", "attr", _attr_block_rule)
     md.core.ruler.after(
@@ -115,7 +140,9 @@ def _find_opening(tokens: Sequence[Token], index: int) -> int | None:
     return None
 
 
-def _span_rule(state: StateInline, silent: bool) -> bool:
+def _span_rule(
+    state: StateInline, silent: bool, *, allowed: set[str] | None = None
+) -> bool:
     if state.src[state.pos] != "[":
         return False
 
@@ -144,7 +171,7 @@ def _span_rule(state: StateInline, silent: bool) -> bool:
         state.pos = labelStart
         state.posMax = labelEnd
         token = state.push("span_open", "span", 1)
-        token.attrs = attrs  # type: ignore[assignment]
+        _add_attrs(state.md, token, attrs, allowed)
         state.md.inline.tokenize(state)
         token = state.push("span_close", "span", -1)
 
@@ -177,7 +204,7 @@ def _attr_inline_rule(
         attr_token = state.tokens[token_index]
         if "class" in attrs and "class" in token.attrs:
             attrs["class"] = f"{token.attrs['class']} {attrs['class']}"
-        _add_attrs(attr_token, attrs, allowed)
+        _add_attrs(state.md, attr_token, attrs, allowed)
     return True
 
 
@@ -253,23 +280,69 @@ def _attr_resolve_block_rule(state: StateCore, *, allowed: set[str] | None) -> N
                     if key == "class" or key not in next_token.attrs:
                         next_token.attrs[key] = value
             else:
-                _add_attrs(next_token, state.tokens[i].attrs, allowed)
+                _add_attrs(state.md, next_token, state.tokens[i].attrs, allowed)
 
         state.tokens.pop(i)
         len_tokens -= 1
 
 
+_URL_ATTRS = frozenset(("href", "src", "action", "formaction", "xlink:href"))
+"""Attributes whose value is a URL, checked with ``md.validateLink``."""
+
+_URL_IGNORED_RE = re.compile(r"[\t\n\r]")
+_URL_STRIP = "".join(chr(i) for i in range(0x21))
+
+
+def _is_insecure_attr(key: str) -> bool:
+    """Return True for event-handler attributes (``on*``, e.g. ``onclick``).
+
+    They execute JavaScript, so they are removed by default
+    when no explicit ``allowed`` list is given.
+    """
+    return key.lower().startswith("on")
+
+
+def _is_valid_url(md: MarkdownIt, value: Any) -> bool:
+    """Return True if ``md.validateLink`` accepts a URL-valued attribute.
+
+    Browsers ignore ASCII tabs and newlines anywhere in a URL,
+    and control characters and spaces around it, before reading its scheme
+    (so ``java<TAB>script:`` is a ``javascript:`` URL).
+    The value is emitted as written, so those characters are removed
+    before it is normalised and validated.
+    """
+    url = _URL_IGNORED_RE.sub("", str(value)).strip(_URL_STRIP)
+    return md.validateLink(md.normalizeLink(url))
+
+
 def _add_attrs(
+    md: MarkdownIt,
     token: Token,
     attrs: dict[str, Any],
     allowed: set[str] | None,
 ) -> None:
-    """Add attributes to a token, skipping any disallowed attributes."""
-    if allowed is not None and (
-        disallowed := {k: v for k, v in attrs.items() if k not in allowed}
-    ):
+    """Add attributes to a token, skipping any disallowed attributes.
+
+    When ``allowed`` is not ``None`` only those names are kept.
+    When it is ``None`` (the default) event-handler (``on*``) attributes
+    are still removed, so untrusted input cannot inject script.
+    In both cases, a URL-valued attribute (``href``, ``src``, ...)
+    is removed if ``md.validateLink`` rejects it.
+    Anything removed is preserved in ``token.meta["insecure_attrs"]``.
+    """
+    if allowed is not None:
+        disallowed = {k: v for k, v in attrs.items() if k not in allowed}
+    else:
+        disallowed = {k: v for k, v in attrs.items() if _is_insecure_attr(k)}
+    disallowed.update(
+        (k, v)
+        for k, v in attrs.items()
+        if k not in disallowed and k.lower() in _URL_ATTRS and not _is_valid_url(md, v)
+    )
+
+    if disallowed:
         token.meta["insecure_attrs"] = disallowed
-        attrs = {k: v for k, v in attrs.items() if k in allowed}
+        attrs = {k: v for k, v in attrs.items() if k not in disallowed}
 
     # attributes takes precedence over existing attributes
     token.attrs.update(attrs)

mdit_py_plugins/dollarmath/index.py

@@ -98,7 +98,7 @@ def dollarmath_plugin(
     if label_renderer is None:
         _label_renderer = (  # noqa: E731
             lambda label: (
-                f'<a href="#{label}" class="mathlabel" title="Permalink to this equation">¶</a>'
+                f'<a href="#{escapeHtml(label)}" class="mathlabel" title="Permalink to this equation">¶</a>'
             )
         )
     else:
@@ -142,7 +142,7 @@ def render_math_block_label(
         env: EnvType,
     ) -> str:
         content = _renderer(str(tokens[idx].content).strip(), {"display_mode": True})
-        _id = tokens[idx].info
+        _id = escapeHtml(tokens[idx].info)
         label = _label_renderer(tokens[idx].info)
         return f'<div id="{_id}" class="math block">\n{label}\n{content}\n</div>\n'
 

mdit_py_plugins/myst_blocks/index.py

@@ -152,7 +152,7 @@ def render_myst_target(
     options: OptionsDict,
     env: EnvType,
 ) -> str:
-    label = tokens[idx].content
+    label = escapeHtml(tokens[idx].content)
     class_name = "myst-target"
     target = f'<a href="#{label}">({label})=</a>'
     return f'<div class="{class_name}">{target}</div>'

mdit_py_plugins/texmath/index.py

@@ -6,7 +6,7 @@
 from typing import TYPE_CHECKING, Any, TypedDict
 
 from markdown_it import MarkdownIt
-from markdown_it.common.utils import charCodeAt
+from markdown_it.common.utils import charCodeAt, escapeHtml
 
 if TYPE_CHECKING:
     from markdown_it.renderer import RendererProtocol
@@ -65,7 +65,8 @@ def render_math_block(
                 env: EnvType,
             ) -> str:
                 return rule_block["tmpl"].format(  # noqa: B023
-                    render(tokens[idx].content, True, macros), tokens[idx].info
+                    render(tokens[idx].content, True, macros),
+                    escapeHtml(tokens[idx].info),
                 )
 
             md.add_render_rule(rule_block["name"], render_math_block)
@@ -169,7 +170,7 @@ def dollar_post(src: str, end: int) -> bool:
 
 
 def render(tex: str, displayMode: bool, macros: Any) -> str:
-    return tex
+    return escapeHtml(tex)
     # TODO better HTML renderer port for math
     # try:
     #     res = katex.renderToString(tex,{throwOnError:False,displayMode,macros})

tests/fixtures/myst_block.md

@@ -52,7 +52,7 @@ Target characters:
 .
 (a bc   |@<>*./_-+:)=
 .
-<div class="myst-target"><a href="#a bc   |@<>*./_-+:">(a bc   |@<>*./_-+:)=</a></div>
+<div class="myst-target"><a href="#a bc   |@&lt;&gt;*./_-+:">(a bc   |@&lt;&gt;*./_-+:)=</a></div>
 .
 
 Empty target:

tests/fixtures/texmath_bracket.md

@@ -23,7 +23,7 @@ simple equation including special html character. (valid=True)
 .
 \(1+1<3\)
 .
-<p><eq>1+1<3</eq></p>
+<p><eq>1+1&lt;3</eq></p>
 .
 
 equation including backslashes. (valid=True)
@@ -239,8 +239,8 @@ multiline equation. (valid=True)
 .
 <section>
 <eqn>\\begin{matrix}
- f & = & 2 + x + 3 \\ 
- & = & 5 + x 
+ f &amp; = &amp; 2 + x + 3 \\ 
+ &amp; = &amp; 5 + x 
 \\end{matrix}</eqn>
 </section>
 .
@@ -253,7 +253,7 @@ vector equation. (valid=True)
 .
 <section>
 <eqn>\\begin{pmatrix}x_2 \\\\ y_2 \\end{pmatrix} = 
-\\begin{pmatrix} A & B \\\\ C & D \\end{pmatrix}\\cdot
+\\begin{pmatrix} A &amp; B \\\\ C &amp; D \\end{pmatrix}\\cdot
 \\begin{pmatrix} x_1 \\\\ y_1 \\end{pmatrix}</eqn>
 </section>
 .

tests/fixtures/texmath_dollar.md

@@ -23,7 +23,7 @@ simple equation including special html character. (valid=True)
 .
 $1+1<3$
 .
-<p><eq>1+1<3</eq></p>
+<p><eq>1+1&lt;3</eq></p>
 .
 
 equation including backslashes. (valid=True)
@@ -239,8 +239,8 @@ $$\\begin{matrix}
 .
 <section>
 <eqn>\\begin{matrix}
- f & = & 2 + x + 3 \\ 
- & = & 5 + x 
+ f &amp; = &amp; 2 + x + 3 \\ 
+ &amp; = &amp; 5 + x 
 \\end{matrix}</eqn>
 </section>
 .
@@ -253,7 +253,7 @@ $$\\begin{pmatrix}x_2 \\\\ y_2 \\end{pmatrix} =
 .
 <section>
 <eqn>\\begin{pmatrix}x_2 \\\\ y_2 \\end{pmatrix} = 
-\\begin{pmatrix} A & B \\\\ C & D \\end{pmatrix}\\cdot
+\\begin{pmatrix} A &amp; B \\\\ C &amp; D \\end{pmatrix}\\cdot
 \\begin{pmatrix} x_1 \\\\ y_1 \\end{pmatrix}</eqn>
 </section>
 .