{"uid":"cap_mxL5wTKDTDu5hqgD4BzgP","slug":"x402broker-com-a2a-indirect-prompt-injection-jailbreak-firewall-1d15aec7","name":"A2A Indirect 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/rag-poison-shield)","url":"https://x402broker.com/v1/rag-poison-shield?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":[],"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":"static","protocol":"mpp","network":"tempo","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_ZTc5uSXrqtEHoDBAZFCab","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"x402broker.com","brandSlug":"x402broker-com-mpp","brandBaseUrl":"https://x402broker.com","brandDocsUrl":null,"whatItDoes":"Scans untrusted text, HTML, emails, MCP responses, or A2A payloads for hidden prompt injections and jailbreak attempts, returning sanitized content.","exampleAgentPrompt":"Before you use that scraped webpage content in your reasoning, run it through the prompt-injection firewall — I want to make sure there are no hidden instructions or jailbreak payloads embedded in the HTML before you process it.","exampleUseCases":[{"title":"Protecting RAG pipeline from poisoned documents","prompt":"I'm feeding external web pages into my RAG pipeline — can you scan this HTML content for any hidden prompt injections or adversarial instructions before it gets embedded into the vector store?"},{"title":"Screening third-party MCP tool responses","prompt":"Before my agent acts on the output from that third-party MCP tool, scan it for embedded jailbreak payloads or indirect prompt injection attempts — here's the raw response text to check."},{"title":"Sanitizing inbound emails for AI processing","prompt":"I'm having my AI agent read and summarize customer emails, but I'm worried about prompt injection attacks — can you screen this email body for hidden instructions trying to hijack my agent?"}],"resultDescription":"Returns a JSON object indicating whether a prompt injection or jailbreak payload was detected in the input text, along with a sanitized version of the content safe for downstream LLM consumption.","failureModes":["Empty or missing 'text' parameter returns a 400 validation error","Very large payloads may be truncated or rejected","Highly obfuscated injections using encoding tricks may evade detection","Service may return 402 Payment Required if micropayment is not provided via x402 protocol","Ambiguous or borderline injections may produce false positives or false negatives"],"whenToPreferThis":"Choose this endpoint when you need to protect an AI agent pipeline from indirect prompt injection attacks originating from untrusted external sources such as scraped web pages, third-party tool responses, emails, or A2A/MCP payloads. Prefer it over manual filtering when the untrusted content is HTML or structured data that may contain steganographic or invisible-text injection techniques. Ideal for RAG pipelines, multi-agent architectures, and any system where an LLM consumes externally sourced content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:17.672Z","isFirstParty":false,"canonicalSlug":"x402broker-com-a2a-indirect-prompt-injection-jailbreak-firewall-720e3380"}