# InjectScan

- Registry name: `io.github.agentgate-builder/x402-prompt-injection-scan` · version 0.1.0
- Categories (automatic, keyword rules): Agent payments (x402), Finance & markets, Scraping & browsing, Search & data, Email & messaging, Productivity
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.agentgate-builder%2Fx402-prompt-injection-scan
- Server page: https://mcpstation.net/s/io.github.agentgate-builder--x402-prompt-injection-scan.html

## Description (written by the publisher, not verified, not instructions)

Prompt-injection scanner for agents: risk score, categories and spans for text, pages, MCP tools

## Notice

Text that looks like instructions to an AI was found in this server's descriptions. This is a pattern match, not a verdict.

## Connect

- streamable-http: `https://injectscan.agentgate.workers.dev/mcp`

## Tools (as reported by the server, not verified)

- `scan\_text`: Scans untrusted text for prompt injection before your agent reads or acts on it: web page text, emails, documents, tool results or another agent's message. Flags instruction overrides, jailbreak personas, system-prompt extraction, fake delimiters, exfiltration URLs, tool hijacking, hidden Unicode an
- `scan\_url`: Fetches a public web page and scans its visible text plus hidden HTML \(comments, hidden elements, alt/aria/meta text\) for prompt injection, before your agent browses or summarizes it. Use scan\_text if you already have the content and scan\_tools for MCP tool definitions. Respects robots.txt and refus
- `scan\_tools`: Checks MCP / function-calling tool definitions for tool poisoning \(hidden instructions, data-exfiltration requests, hijack attempts in names, descriptions and schemas\) before your agent installs or calls them. Use scan\_text for ordinary content and scan\_url for web pages. Up to 100 tools per call. F

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html