fix(gmail): sanitize HTML entities and tags in tool output

Gmail API returns snippets with HTML entities (&, ', <br>, etc.) that leaked into LLM responses as raw HTML. Added shared sanitizeHtml() utility in src/utils/html.ts and applied it to gmail tool snippets, HTML body fallback, and gmail watcher snippets.
2026-02-10 16:30:14 -08:00
parent 4317492e4b
commit 4ce8e81c01
6 changed files with 281 additions and 4 deletions
@@ -191,6 +191,36 @@ describe('gmail.list', () => {
    expect(result.success).toBe(true);
    expect(result.output).toBe('No messages found.');
  });
+
+  it('sanitizes HTML entities in snippets', async () => {
+    setupValidAuth();
+    mockMessagesList.mockResolvedValue({
+      data: {
+        messages: [{ id: 'msg1' }],
+      },
+    });
+    mockMessagesGet.mockResolvedValueOnce(
+      mockMessageDetails(
+        'msg1',
+        'experian@test.com',
+        'Credit Alert',
+        'Mon, 10 Feb 2026',
+        'William, your score is rising&#39;s &amp; it&#8230; Don&apos;t miss out<br>Check now',
+      ),
+    );
+
+    const [listTool] = createGmailTools(testConfig);
+    const result = await listTool.execute({});
+
+    expect(result.success).toBe(true);
+    expect(result.output).not.toContain('&#39;');
+    expect(result.output).not.toContain('&amp;');
+    expect(result.output).not.toContain('&#8230;');
+    expect(result.output).not.toContain('<br>');
+    expect(result.output).toContain("rising's");
+    expect(result.output).toContain('& it');
+    expect(result.output).toContain("Don't miss out");
+  });
 });

 describe('gmail.search', () => {
@@ -360,6 +390,38 @@ describe('gmail.read', () => {
    expect(result.output).not.toContain('<html>');
  });

+  it('decodes HTML entities in HTML-only body fallback', async () => {
+    setupValidAuth();
+    const htmlBody = '<html><body><p>Hello &amp; welcome</p><br><p>Price: &lt;$100&gt;</p><br><p>It&#39;s great</p></body></html>';
+    mockMessagesGet.mockResolvedValue({
+      data: {
+        payload: {
+          mimeType: 'multipart/alternative',
+          headers: [
+            { name: 'From', value: 'sender@example.com' },
+            { name: 'To', value: 'will@example.com' },
+            { name: 'Subject', value: 'HTML Entities' },
+            { name: 'Date', value: 'Mon, 10 Feb 2026 12:00:00 -0000' },
+          ],
+          parts: [
+            { mimeType: 'text/html', body: { data: toBase64Url(htmlBody) } },
+          ],
+        },
+      },
+    });
+
+    const [, , readTool] = createGmailTools(testConfig);
+    const result = await readTool.execute({ id: 'msg-entities' });
+
+    expect(result.success).toBe(true);
+    expect(result.output).toContain('Hello & welcome');
+    expect(result.output).toContain('Price: <$100>');
+    expect(result.output).toContain("It's great");
+    expect(result.output).not.toContain('&amp;');
+    expect(result.output).not.toContain('&lt;');
+    expect(result.output).not.toContain('&#39;');
+  });
+
  it('returns error when credentials missing', async () => {
    mockExistsSync.mockReturnValue(false);
    const [, , readTool] = createGmailTools(testConfig);
@@ -4,6 +4,7 @@ import { resolve } from 'path';
 import { homedir } from 'os';
 import type { GmailConfig } from '../../config/schema.js';
 import type { Tool, ToolResult } from '../types.js';
+import { sanitizeHtml } from '../../utils/html.js';

 /** Expand ~ to home directory. */
 function expandPath(p: string): string {
@@ -79,7 +80,7 @@ async function fetchMessageDetails(
      from: getHeader('From'),
      subject: getHeader('Subject'),
      date: getHeader('Date'),
-      snippet: msg.data.snippet ?? '',
+      snippet: sanitizeHtml(msg.data.snippet ?? ''),
    };
  } catch {
    return null;
@@ -123,8 +124,8 @@ function extractTextBody(payload: {
      }
    }
    if (htmlFallback) {
-      // Strip HTML tags for a rough plain-text rendering
-      return htmlFallback.replace(/<[^>]+>/g, '').replace(/\s+/g, ' ').trim();
+      // Convert HTML to clean plain text
+      return sanitizeHtml(htmlFallback);
    }
  }