Prompt-injection detector

{
  "name": "Prompt-injection detector",
  "tags": [
    "security",
    "guardrail",
    "prompt-injection",
    "llm-safety"
  ],
  "type": "https://eips.ethereum.org/EIPS/eip-8004",
  "services": [
    {
      "name": "https://agent.hpp.io/paid/compute/promptguard",
      "method": "POST",
      "endpoint": "https://agent.hpp.io/paid/compute/promptguard",
      "transport": "http",
      "description": "Checks whether a piece of text is trying to hijack an AI assistant - for example hidden instructions like 'ignore your rules and...'. A safety filter for anything an AI agent reads from users, web pages, or tools. Send the text, and it comes back as safe or injection with a confidence score. A protective signal, not a guarantee.",
      "paymentRequired": true
    },
    {
      "name": "compute_promptguard",
      "endpoint": "https://agent.hpp.io/mcp/tools/compute_promptguard",
      "toolName": "compute_promptguard",
      "transport": "mcp",
      "description": "Checks whether a piece of text is trying to hijack an AI assistant - for example hidden instructions like 'ignore your rules and...'. A safety filter for anything an AI agent reads from users, web pages, or tools. Send the text, and it comes back as safe or injection with a confidence score. A protective signal, not a guarantee.",
      "paymentRequired": true
    }
  ],
  "description": "Checks whether a piece of text is trying to hijack an AI assistant - for example hidden instructions like 'ignore your rules and...'. A safety filter for anything an AI agent reads from users, web pages, or tools. Send the text, and it comes back as safe or injection with a confidence score. A protective signal, not a guarantee.",
  "x402Support": true,
  "supportedTrust": [
    "feedback"
  ]
}