Covered categories
Instruction overrides, role hijacking, prompt extraction, data-exfiltration wording, fake delimiters, encoding/obfuscation, invisible Unicode, and hidden HTML content.
How the detector works
Prompt Injection Check uses deterministic, explainable browser rules. The core function accepts plain text and returns structured findings; it does not call an AI model or upload scan content.
Interpretation
Results are warning signals, not a calibrated probability or a safety verdict. A finding includes a category, severity, matched span, explanation, and stable rule ID.
Known limitations
Rules can miss paraphrased, multilingual, image-based, novel, or context-dependent attacks. Quoted documentation and legitimate role-play can produce false positives. Use least privilege, sandboxing, and human approval for consequential workflows.
Future npm/CLI shape
The detector is intentionally separated from the UI so it can later be
imported as scanText(text) or exposed through a CLI
without changing the website. No public API or package is published
yet.