Launcher for the standalone AI: scan text against twelve injection patterns with severities and a risk score, get a sanitised copy, and read the defences that actually hold. In-browser.
The injection lab is part of the standalone AI’s Prompt studio: heuristic patterns for instruction override, role spoofing, exfiltration and more, each with severity and matched context, plus a sanitiser and a list of defences that hold in practice.
Open in the standalone AIOpens at: Prompt studio → injection scanner · runs entirely in your browser · no account, no API key, nothing uploaded
The interactive tool that used to live on this card now runs inside the standalone AI at ai.html, where it shares your indexed documents, stored memories and every reasoning method. This card stays in the catalogue as a launcher so existing links keep working.