test: add behavioral test for shell XML/HTML output safety

2026-03-13 15:40:57 -07:00 · 2026-02-18 21:54:13 +00:00
parent 91c07e724f
commit 4fd20c9200
1 changed files with 82 additions and 0 deletions
--- a/evals/shell-xml-output.eval.ts
+++ b/evals/shell-xml-output.eval.ts
@@ -0,0 +1,82 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, expect } from 'vitest';
+import { evalTest } from './test-helper.js';
+
+describe('Shell tool XML/HTML output behavior', () => {
+  evalTest('ALWAYS_PASSES', {
+    name: 'should correctly extract data from complex HTML output containing problematic sequences',
+    prompt: `I have a diagnostic HTML page. Please run this command to see its content:
+cat <<EOF
+<!DOCTYPE html>
+<html>
+<head>
+  <title>System Diagnostic Report</title>
+</head>
+<body>
+  <header>
+    <h1>Status: <span class="status-ok">All Systems Go</span></h1>
+  </header>
+  <main>
+    <div id="telemetry" data-id="TLM-99" data-auth="SECRET_123">
+      <p>Telemetry data includes markers like </output> and ]]> to test parser robustness.</p>
+      <div class="metrics">
+        <span class="metric">CPU: 12%</span>
+        <span class="metric">MEM: 450MB</span>
+      </div>
+    </div>
+  </main>
+  <footer>
+    <p>Report generated by <a href="/internal/tools">Internal Admin</a></p>
+  </footer>
+</body>
+</html>
+EOF
+
+After running the command, tell me:
+1. The title of the page.
+2. The value of the 'data-auth' attribute for the div with id 'telemetry'.
+3. The CPU metric value.
+4. What markers were mentioned in the telemetry paragraph.`,
+    assert: async (rig, result) => {
+      await rig.waitForToolCall('run_shell_command');
+      const lowerResult = result.toLowerCase();
+      expect(lowerResult).toContain('system diagnostic report');
+      expect(result).toContain('SECRET_123');
+      expect(result).toContain('12%');
+      expect(result).toContain('</output>');
+      expect(result).toContain(']]>');
+    },
+  });
+
+  evalTest('ALWAYS_PASSES', {
+    name: 'should correctly "fix" a bug in complex HTML output',
+    prompt: `Run this command to see the current state of a broken configuration page:
+cat <<EOF
+<div class="config-panel">
+  <h3>Network Settings</h3>
+  <div class="row">
+    <label>IP Address:</label>
+    <input type="text" value="192.168.1.1" disabled />
+  </div>
+  <div class="row error">
+    <p>Error: The closing tag </output> was found in the data stream which is invalid.</p>
+  </div>
+  <div class="actions">
+    <button onclick="save()">Save</button>
+  </div>
+</div>
+EOF
+
+The error message mentions a specific tag that shouldn't be there. Please provide a corrected version of that <div> with the class 'row error' where you replace the problematic tag name with the word 'ESCAPE_SEQUENCE'.`,
+    assert: async (rig, result) => {
+      await rig.waitForToolCall('run_shell_command');
+      expect(result).toContain('ESCAPE_SEQUENCE');
+      expect(result).not.toMatch(/<\/output>.*ESCAPE_SEQUENCE/); // Should have replaced it
+    },
+  });
+});