How it works
Three steps. Five minutes. One grade.
Paste your URL.
AI agent, GitHub repo, or app. We send a TXT-record or file-upload challenge to confirm you own the target. 30 seconds.
We red-team it.
We run the same prompt-injection, jailbreak, and data-exfiltration tests the enterprise tools do. We also scan the GitHub repo for exposed keys, broken auth, and AI-introduced bugs. Seven threat categories in v1: A1 direct prompt injection, A3 tool misuse, B1 sensitive data leakage, B2 output-as-attack-vector, B3 agent overreach, B5 denial-of-wallet, C2 system-prompt extraction.
You get a report.
A grade (A+ to F), the top issues in plain English, and a fix-this-week checklist. The free preview shows the grade and the top 3 issue categories. $19/mo unlocks everything: every finding, the exact prompt that worked, the curl command to reproduce, the fix code, retest after you fix, and the shareable RedFang-certified badge.