# Injectscan

> Prompt-injection scan for text your AI agent is about to read (web pages, emails, tool output, MCP tool descriptions): risk score 0-100, verdict, categories and exact spans. Detects instruction overrides, jailbreak personas, system-prompt extraction, fake chat delimiters, data-exfiltration URLs, tool hijacking, hidden Unicode and encoded payloads. Deterministic rules, no data stored.

- **Domain**: `injectscan.agentgate.workers.dev`
- **Provider**: injectscan.agentgate.workers.dev (https://injectscan.agentgate.workers.dev/)
- **Kind**: paid_api
- **Live-responds (last probe)**: None
- **Signed card**: False
- **Streaming**: False
- **Quality score**: 70%
- **Payment protocol**: x402 · network `eip155:8453` · ≥ $0.003
- **Wallet**: `0x3c1a1e01e790cd326495631b3b38bd7068f08d6f`

## URLs
- Agent card: https://injectscan.agentgate.workers.dev/
- Page (HTML): https://agenstry.com/agents/injectscan.agentgate.workers.dev
- Documentation: https://injectscan.agentgate.workers.dev/v1/scan