From 2c7ca256bbfdca1a8ae02c6b2b1009ba62f1167b Mon Sep 17 00:00:00 2001
From: Dipanshu Singh <singhdipanshu133@gmail.com>
Date: Sat, 23 May 2026 09:39:42 +0530
Subject: [PATCH] Fix raw-text sanitization bypass vulnerability and add
 regression tests

---
 packages/sanitize-html/index.js     |  4 +--
 packages/sanitize-html/test/test.js | 56 +++++++++++++++++++++++++++++
 2 files changed, 58 insertions(+), 2 deletions(-)

diff --git a/packages/sanitize-html/index.js b/packages/sanitize-html/index.js
index 6a67683868..b5da859f7e 100644
--- a/packages/sanitize-html/index.js
+++ b/packages/sanitize-html/index.js
@@ -566,13 +566,13 @@ function sanitizeHtml(html, options, _recursing) {
 
       if (options.disallowedTagsMode === 'completelyDiscard' && !tagAllowed(tag)) {
         text = '';
-      } else if ((options.disallowedTagsMode === 'discard' || options.disallowedTagsMode === 'completelyDiscard') && ((tag === 'script') || (tag === 'style'))) {
+      } else if (tag && tagAllowed(tag) && (options.disallowedTagsMode === 'discard' || options.disallowedTagsMode === 'completelyDiscard') && ((tag === 'script') || (tag === 'style'))) {
         // htmlparser2 gives us these as-is. Escaping them ruins the content. Allowing
         // script tags is, by definition, game over for XSS protection, so if that's
         // your concern, don't allow them. The same is essentially true for style tags
         // which have their own collection of XSS vectors.
         result += text;
-      } else if ((options.disallowedTagsMode === 'discard' || options.disallowedTagsMode === 'completelyDiscard') && (tag === 'textarea' || tag === 'xmp')) {
+      } else if (tag && tagAllowed(tag) && (options.disallowedTagsMode === 'discard' || options.disallowedTagsMode === 'completelyDiscard') && (tag === 'textarea' || tag === 'xmp')) {
         // htmlparser2 treats <textarea> and <xmp> as raw text elements and
         // does NOT decode entities inside them. The text is already properly
         // encoded, so pass it through without additional escaping to avoid
diff --git a/packages/sanitize-html/test/test.js b/packages/sanitize-html/test/test.js
index 5bd342e530..f757d7f286 100644
--- a/packages/sanitize-html/test/test.js
+++ b/packages/sanitize-html/test/test.js
@@ -1931,4 +1931,60 @@ describe('sanitizeHtml', function() {
       ), '!<xmp>&lt;/xmp&gt;&lt;svg/onload=prompt`xs`&gt;</xmp>!'
     );
   });
+
+  describe('CVE-2026-44990 regression and raw-text edge cases', function() {
+    it('should escape raw-text inner content when xmp tag is disallowed and discarded under custom nonTextTags', function() {
+      assert.strictEqual(
+        sanitizeHtml('<xmp><script>alert(1)</script></xmp>', {
+          nonTextTags: ['script', 'style']
+        }),
+        '&lt;script&gt;alert(1)&lt;/script&gt;'
+      );
+    });
+
+    it('should escape raw-text inner content when script tag is disallowed and discarded under empty nonTextTags', function() {
+      assert.strictEqual(
+        sanitizeHtml('<script><svg onload=alert(1)></script>', {
+          nonTextTags: []
+        }),
+        '&lt;svg onload=alert(1)&gt;'
+      );
+    });
+
+    it('should escape raw-text inner content when textarea tag is disallowed and discarded', function() {
+      assert.strictEqual(
+        sanitizeHtml('<textarea><script>alert(1)</script></textarea>', {
+          nonTextTags: []
+        }),
+        '&lt;script&gt;alert(1)&lt;/script&gt;'
+      );
+    });
+
+    it('should escape raw-text inner content when style tag is disallowed and discarded', function() {
+      assert.strictEqual(
+        sanitizeHtml('<style><a onload=alert(1)></style>', {
+          nonTextTags: []
+        }),
+        '&lt;a onload=alert(1)&gt;'
+      );
+    });
+
+    it('should handle malformed or unclosed raw-text tags correctly', function() {
+      assert.strictEqual(
+        sanitizeHtml('<xmp><script>alert(1)', {
+          nonTextTags: ['script', 'style']
+        }),
+        '&lt;script&gt;alert(1)'
+      );
+    });
+
+    it('should handle sibling raw-text elements correctly without leaking states', function() {
+      assert.strictEqual(
+        sanitizeHtml('<noembed><script>alert(1)</script></noembed><noscript><style>body{}</style></noscript>', {
+          nonTextTags: []
+        }),
+        'alert(1)body{}'
+      );
+    });
+  });
 });