ShadowLab

Chaos engineering for AI APIs

Powered by DigitalOcean Gradientâ„¢ AI

Automatically uncover adversarial failures before they reach production.

New scan

e.g. https://api.example.com/v1/chat or http://localhost:8000/mock-vulnerable-api

Optional — used to tailor adversarial prompts when using Gradient AI.

For OpenAI/Gradient endpoints when using messages format.

For real API demos (e.g. Gradient). Not stored; sent only with the scan request.

Run a scan to see your security score.

Scan Status

Waiting for scan...