Runs in your browser. Nothing you enter is uploaded or logged.
One useful email every Monday
New free tools, AI and network threats that matter, and one quick challenge. No spam, unsubscribe in one click.
How to use it
- 1
Paste text or open a PDF, DOCX or HTML file.
- 2
Review flagged instructions, hidden text and invisible characters.
- 3
Copy the cleaned text before you give it to an AI.
Questions people ask
Is my document uploaded anywhere?
No. The scan runs in your browser with JavaScript. Nothing you paste or open is sent to our servers or logged.
What is indirect prompt injection?
Instructions hidden in content an AI reads, such as white text in a PDF or an HTML comment, that try to make the AI do something the user did not ask for.
Can a scanner catch every injection?
No. Pattern scanning catches common and hidden techniques. Treat a clean result as reduced risk and still limit what your AI can do.
Related tools
- IOC extractorPull IPs, domains, URLs, hashes and emails out of any text, refanged and deduplicated.
- Secrets & PII scannerDetect and redact API keys, passwords, cards and personal data before you paste into AI.
- Quick paste checkOne-box leak check with a redacted copy and injection patterns.
- MCP tool scannerCatch tool poisoning, hidden instructions and risky configs in MCP servers.
- MCP client config reviewUnpinned packages, shell access, broad file access and plain-text secrets.
- Model file scannerCheck .pt, .pkl, .bin and other model files for code that runs when loaded.
Link to this tool
Found it useful? Paste this into your blog, wiki or runbook.
<a href="https://toolbini.com/ai/prompt-injection-scanner/">Prompt-injection scanner</a>Reviewed by the editorial team · Last reviewed 2026-11 · Report an error