LockLLM - Free Prompt Injection Scanner

LockLLM is a free extension that helps you scan prompts and documents for prompt injection attacks, jailbreak attempts, hidden text, and malicious instructions before you paste them into AI tools like ChatGPT, Claude, Gemini, and more. It is built for developers, security teams, researchers, and everyday users who want a quick safety check on suspicious text and documents. ✨ How Does LockLLM Work? LockLLM analyzes text through the LockLLM scanning API and returns a clear verdict in seconds. You can scan text in the extension popup, scan selected text with right-click, upload files to extract and scan their contents, or enable Auto-Scan to scan text you copy or paste. 🎯 Key Features: ✅ Prompt Injection Detection Detect malicious instructions, hidden commands, and prompt-based exploits before they reach your AI workflow. 🧨 Jailbreak and Policy Bypass Detection Catch common jailbreak patterns and attempts to override safety rules. 🛡️ System Prompt and Secret Extraction Defense Identify prompts that try to reveal hidden instructions, private context, or sensitive information. 🎭 Instruction Override and Role Manipulation Detection Detect hierarchy abuse like “ignore previous instructions” and roleplay-based coercion. 🧠 Agent and Tool Abuse Signals Flag suspicious patterns commonly used to hijack agent behavior or misuse tools and function calls. 📚 RAG and Document Injection Scanning Scan text from retrieved documents and uploads to identify poisoned context and embedded malicious instructions. 🧩 Indirect Injection Scanning Find attacks hidden inside webpages, notes, PDFs, and other content you copy, paste, or upload. 🕵️ Evasion and Obfuscation Detection Catch attempts to hide attacks using encoding tricks, hidden text, whitespace manipulation, and other evasion methods. ⚡ Auto-Scan (Copy and Paste) When enabled in Settings, LockLLM automatically scans text you copy or paste and shows warnings when risky content is detected. You can toggle this on or off anytime. 🖱️ Right-Click Quick Scan Scan highlighted text instantly using the context menu for fast checks while browsing. 📄 File Upload Scanning Upload PDFs and common text-based formats in the extension, extract text, and scan it without leaving your browser. 🧾 Clear Results and Debug Output See safe or malicious status, injection score, confidence, scan duration, and a request ID. Debug JSON is available in the extension UI when needed. 💡 Use Cases: 🧑‍💻 For Developers Test prompts before deployment, validate user input, and harden chatbots and agent workflows. 🛡️ For Security Teams Audit AI inputs, test for prompt injection vulnerabilities, and validate security policies. 🔬 For Researchers and Students Study prompt injection techniques, test robustness, and analyze attack patterns. 🙌 For Everyone Verify suspicious text before sharing it with an AI assistant, and check documents before uploading to AI tools. 🔐 Privacy and Permissions: • The extension sends only the text you choose to scan, and text captured by Auto-Scan only if you enable it in Settings • No browsing history access • No storing of prompts or personal data ⚡ Get Started: 1) Install the extension 2) Open Settings and add your free LockLLM API key 3) Paste, select, copy, or upload content and scan in seconds Protect your prompts and documents before they reach your AI systems. Install LockLLM and prompt with confidence.