{"type":"https://eips.ethereum.org/EIPS/eip-8004","name":"Prompt-injection detector","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,"tags":["security","guardrail","prompt-injection","llm-safety"],"services":[{"name":"https://agent.hpp.io/paid/compute/promptguard","endpoint":"https://agent.hpp.io/paid/compute/promptguard","method":"POST","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","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.","toolName":"compute_promptguard","paymentRequired":true}],"supportedTrust":["feedback"]}