Claude In Chrome Troubleshooting

TL;DR

• 目的：Perform claude in chrome troubleshooting assessment during authorized security testing. Use this skill when indicators of the vulnerability class are
• 适用：通用
• 输入：目标信息
• 输出：执行结果 + 证据
• 红线：仅限授权范围内；扫描限速 -c 10 -rl 10；所有动作记 oplog
• 关联：上游：所有 2-web-vulns skill → 下游：003-src-session-start

Original skill by @jeffzwang from @ExaAILabs. Enhanced and updated for current versions of Claude Desktop and Claude Code.

When to Use

• Target presents indicators of the vulnerability class this skill covers
• Fingerprint or recon indicates the relevant technology stack is in use
• Authorized testing scope covers the target endpoint or component
• Findings need to be validated through this skill's methodology

Diagnostic Workflow

1. Check Chrome extension status — Navigate to chrome://extensions/ and verify Claude extension is enabled
2. Verify MCP server — Open Claude Desktop → Settings → Developer → Check MCP servers
3. Test connection — Use mcp__claude-in-chrome__* tools (e.g., screenshot) to verify connectivity
4. Check console — Open Chrome DevTools (F12) → Console tab for errors
5. Restart if needed — Disable/enable extension, restart Claude Desktop

Common Issues

• "Browser extension is not connected" — Extension was disabled or browser was restarted without extension
• "Permission denied" — Chrome permissions for the site need to be granted
• "Tab not found" — Tab was closed before tool call
• "Timeout" — Network issues or browser is frozen

Fallback Strategy

If Claude in Chrome MCP is unavailable:

1. Use mcp__playwright for browser automation (alternative MCP)
2. Use curl + jq for direct HTTP testing
3. Use Burp Suite with manual browser testing

When NOT to Use

• Target is clearly outside this skill's scope (refer to related skills)
• No authorization for testing
• Need a different category of testing (use related skills)