Shadow Prompt Detection Tool

Detect hidden prompts in AI content

Hidden or shadow prompts are instructions concealed in content, in white text, metadata, or an image, meant to manipulate an AI that processes it. This tool detects hidden or shadow prompts in AI interactions, so you can catch manipulation that a human would not see.

Why hidden prompts are a real threat

As AI systems process web pages, documents and images, attackers hide instructions in that content, invisible to a human but read by the model, to make it behave against its purpose, a form of indirect prompt injection. A page might contain hidden text telling an AI assistant to ignore its instructions or leak data. Detecting these concealed prompts before or as content is processed is a defensive control, because the human reviewing the content would never see them. This is defensive analysis to protect an AI system that ingests external content.

See what the model sees

The tool runs entirely in your browser, so nothing you paste, prompts, outputs or documents, is uploaded, which matters when the input is sensitive AI data or your own content.

Related tools

• AI Prompt Leakage Analyzer — Paste a system prompt and a hostile user input to see whether the prompt holds secrets and whether the input carries injection patterns. Local, instant.
• LLM Data Exposure Checker — Check if text contains data likely to be memorized or exposed by LLMs.
• AI Usage Policy Generator — Generate an acceptable use policy for AI tools in your company.
• Model Hallucination Estimator — Estimate risk of hallucinations based on task type and temperature.