Deterministic RU/EN safety preflight for AI-agent prompts and tasks. Flags six risk families: prompt injection, secret exfiltration, wallet signing or spend, spam or impersonation, destructive operations, and credential harvesting. POST JSON {"text":"..."}; advisory signals only, no LLM, no request-body storage, no security guarantee.
Api EndpointSecurityReachable · 1419 ms0.001 USDC0.001 USDC · eip155:8453 · USDC
https://proofgate-agent-safety.arinagame1993.chatgpt.site/v1/scan