Agent Input Guard
Prompt injection and tool abuse heuristic scanner with x402 USDC payment on Base. Verified route: POST /scan at 0.002 USDC, taking {text} and returning a risk level, score, finding count, matched patterns and a recommendation. Verified with a non advertised credential exfiltration prompt, where it returned a structured medium risk result quoting the matching substring from the submitted text. Heuristic only: false positives and misses are possible. Base only.
x402 verified · Verified on /scan · $0.002 · $0.002 USDC/request · 1 endpoints · Tools · base network · x402 protocol
How to call this API
Every protected route returns HTTP 402 with x402 payment requirements. An agent pays the stated USDC amount on Base and retries with the payment header. No API keys, no accounts. Browse the marketplace or list your own API.