From 3d5baf13f41bf0e35c8b1e57f1d5119dbdaaaf3f Mon Sep 17 00:00:00 2001
From: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com>
Date: Wed, 16 Sep 2026 23:57:14 -0300
Subject: [PATCH] fix(providers): strip Vertex doc script blocks whose end tag
 carries junk (#13936)

The Vertex model-docs HTML is converted to plain text before the table
parser reads context-window and token-limit numbers out of the cells.
The script/style removal pass required the end tag to be `</script\s*>`,
but the HTML spec closes the element on `</script\t\n foo>` too. Such a
block survived the pass; the generic `<[^>]+>` strip below then removed
both tags and kept the script BODY, so text that only ever existed inside
a script became cell text the number parser trusts.

Accept any end tag that starts with `</script`/`</style` followed by a
tag-name boundary, matching what a browser does.

CodeQL js/bad-tag-filter, alert #1007.
---
 .../fixes/vertex-docs-script-end-tag.md        |  1 +
 src/lib/providerModels/vertexModelMetadata.ts  |  6 +++++-
 tests/unit/vertex-model-metadata.test.ts       | 18 ++++++++++++++++++
 3 files changed, 24 insertions(+), 1 deletion(-)
 create mode 100644 changelog.d/fixes/vertex-docs-script-end-tag.md

diff --git a/changelog.d/fixes/vertex-docs-script-end-tag.md b/changelog.d/fixes/vertex-docs-script-end-tag.md
new file mode 100644
index 0000000000..fd7ce17d9f
--- /dev/null
+++ b/changelog.d/fixes/vertex-docs-script-end-tag.md
@@ -0,0 +1 @@
+- **fix(providers):** strip `<script>`/`<style>` blocks from the Vertex model-docs HTML even when the end tag carries junk before the `>` (`</script foo>`, which the HTML spec still treats as a close). The old regexp required `</script\s*>`, so such a block survived; the generic tag-stripping pass then removed both tags and kept the script BODY, letting its text reach the table cells the context-window/token-limit parser reads (CodeQL `js/bad-tag-filter`, alert #1007).
diff --git a/src/lib/providerModels/vertexModelMetadata.ts b/src/lib/providerModels/vertexModelMetadata.ts
index 53409dfb9b..65b134758b 100644
--- a/src/lib/providerModels/vertexModelMetadata.ts
+++ b/src/lib/providerModels/vertexModelMetadata.ts
@@ -147,7 +147,11 @@ function decodeHtmlEntities(value: string): string {
 function htmlFragmentToText(fragment: string): string {
   return decodeHtmlEntities(
     fragment
-      .replace(/<(?:script|style)\b[^>]*>[\s\S]*?<\/(?:script|style)\s*>/gi, " ")
+      // The end tag accepts junk before the `>` — `</script\t\n bar>` closes the element per the
+      // HTML spec. Matching only `\s*>` left such a block unremoved here; the generic `<[^>]+>`
+      // pass below then stripped both tags and kept the script BODY, so whatever it contained
+      // landed in the cell text the number parser reads (CodeQL js/bad-tag-filter, alert #1007).
+      .replace(/<(?:script|style)\b[^>]*>[\s\S]*?<\/(?:script|style)\b[^>]*>/gi, " ")
       .replace(/<(?:br|hr)\b[^>]*\/?\s*>/gi, " ")
       .replace(/<[^>]+>/g, " ")
   )
diff --git a/tests/unit/vertex-model-metadata.test.ts b/tests/unit/vertex-model-metadata.test.ts
index 5752d94556..4c37a1b8e7 100644
--- a/tests/unit/vertex-model-metadata.test.ts
+++ b/tests/unit/vertex-model-metadata.test.ts
@@ -163,3 +163,21 @@ test("Vertex normalization persists context separately while legacy providers re
   ]);
   assert.equal(normalizeDiscoveredModels([metadata], "openrouter")[0]?.inputTokenLimit, 1048576);
 });
+
+test("#1007: a spec-legal `</script foo>` end tag does not leak script text into a parsed cell", () => {
+  // CodeQL js/bad-tag-filter: the script/style stripper matched only `</script>` with optional
+  // whitespace, but HTML also accepts junk before the `>` — `</script\t\n bar>` closes the element.
+  // The generic `<[^>]+>` pass then removes both tags, so what survives is the script BODY, which
+  // lands in the cell text the number parser reads. Docs pages come from docs.cloud.google.com and
+  // are parsed to TEXT (never rendered), so the impact is a poisoned limit, not injection.
+  const html = modelDocsHtml(`
+    <tr><th>Model ID</th><td>gemini-3.7-flash</td></tr>
+    <tr><th>Token limits</th><td>Context window</td><td><script>999,999,999</script\t\n bar></td></tr>
+  `);
+
+  assert.equal(
+    parseVertexModelDocsHtml(html, "gemini-3.7-flash"),
+    null,
+    "a number that exists only inside a script body must not become the model's context window"
+  );
+});