ContextHound

Real-time prompt injection scanner. Detect injection attacks before they reach your AI model.

ContextHound scans text you type into AI tools for prompt injection attacks attempts by malicious content to hijack, manipulate, or jailbreak the AI model you are using. HOW IT WORKS A lightweight scan pill appears next to any AI chat input on any website. As you type, ContextHound analyses the text against 70 detection rules covering jailbreaks, role-hijack instructions, indirect injection, data exfiltration attempts, system-prompt overrides, and more. A risk score and explanation appear instantly. DEVTOOLS PANEL Open Chrome DevTools and select the ContextHound tab to monitor live LLM API traffic. The panel intercepts requests to AI models , scanning both the request and response for injection content. POPUP SCANNER Click the toolbar icon to paste and scan any text manually - useful for checking content before you share it with a model. SETTINGS Filter findings by severity, toggle the toolbar badge, and block the extension on specific domains if needed. PRIVACY Everything runs entirely in your browser. No text, prompt content, scan results, or metadata is collected, stored externally, or transmitted anywhere. The extension has no backend server. OPEN SOURCE The full source code is available on GitHub. Contributions and rule suggestions are welcome.