{"uid":"cap_0nFB6wTX1BJ6E5uVEWn_Z","slug":"x402broker-prompt-injection-jailbreak-firewall-f163a4d6","name":"x402broker Prompt Injection & Jailbreak Firewall","description":"Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized text. (Live x402 v2, IETF MPP & MCP endpoint at https://x402broker.com/v1/prompt-firewall)","url":"https://x402broker.com/v1/prompt-firewall?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","required":["text"],"properties":{"text":{"type":"string","minLength":1,"description":"Untrusted text, HTML, or tool output to scan for hidden prompt injection or jailbreak payloads"}}},"responseSchema":{"type":"object"},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.005","displayCostAsset":"USD","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.005/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"unknown","protocol":"x402","network":"base","amountUsd":null,"per":"call","confidence":"unknown"},{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_QewOJftZM_KYtEAhcgFr6","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null},{"uid":"pm_BziCsbZl8HWTv1fLYOzmg","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Scans untrusted text (web pages, emails, MCP responses, A2A payloads) for hidden prompt injections and jailbreak attempts, returning sanitized content.","exampleAgentPrompt":"Before you summarize that web page content, run it through the prompt injection firewall to check for any hidden jailbreak instructions embedded in the text.","exampleUseCases":[{"title":"Sanitize scraped web content for agent pipeline","prompt":"I'm building an agent that scrapes product pages and summarizes them — can you scan this page text through the prompt firewall first to make sure there are no hidden instructions trying to hijack my agent?"},{"title":"Screen incoming emails before AI processing","prompt":"Before my AI assistant processes this customer email, can you check it for any embedded prompt injection attempts or jailbreak payloads that might manipulate the agent?"},{"title":"Validate MCP tool response before acting","prompt":"My agent just got a response back from an external MCP tool — can you run it through the prompt injection scanner to make sure there's nothing in there trying to override my agent's instructions before we act on it?"}],"resultDescription":"Returns a sanitized version of the input text with hidden prompt injections removed or flagged, along with detection signals indicating whether injection attempts or jailbreak patterns were found in the original content.","failureModes":["Missing required 'text' query parameter returns an error","Extremely long input may be truncated or rejected","Obfuscated or novel injection patterns may evade detection","Non-text or binary content may not be handled correctly","Payment failure (x402) blocks the request"],"whenToPreferThis":"Choose this endpoint when you need to safely process untrusted external content (web pages, emails, API responses, tool outputs) before feeding it into an LLM or agentic pipeline. Ideal for multi-agent systems, MCP orchestration, and A2A workflows where indirect prompt injection is a real attack surface. Prefer this over generic content filters when your threat model specifically includes adversarial text trying to manipulate an AI agent's behavior.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T12:48:20.194Z","isFirstParty":false,"canonicalSlug":"x402broker-prompt-injection-jailbreak-firewall-f163a4d6"}