{"uid":"cap_-b6tTXJVaEgxT3JcOMfA2","slug":"onchain-risk-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-55de4c5d","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://onchain-risk.agentdiet.dev/v1/prompt-injection-shield)","url":"https://onchain-risk.agentdiet.dev/v1/prompt-injection-shield?utm_source=zero.xyz","method":"POST","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_GY4XGAerjKnVZBZhYK19Q","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"onchain-risk.agentdiet.dev","brandSlug":"onchain-risk-agentdiet-dev-mpp","brandBaseUrl":"https://onchain-risk.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Scans untrusted text, HTML, emails, MCP responses, or A2A payloads for hidden prompt injection and jailbreak attempts, returning sanitized content.","exampleAgentPrompt":"Before you process the content from that scraped webpage, run it through the prompt injection firewall first — I need to make sure there are no hidden instructions or jailbreak payloads embedded in the HTML trying to hijack you.","exampleUseCases":[{"title":"Securing agent email processing pipeline","prompt":"I have an AI agent that reads and summarizes customer emails — before it processes each one, can you scan the raw email body for any hidden prompt injections or jailbreak attempts that might try to override my agent's instructions?"},{"title":"Sanitizing MCP tool output before LLM use","prompt":"My agent just got a response back from an external MCP tool and I'm not sure I trust it — can you scan that tool output for any embedded prompt injection payloads before I pass it into the language model context?"},{"title":"Screening scraped web content for injections","prompt":"I'm building a research agent that pulls content from arbitrary websites — scan this HTML I just scraped from an untrusted site and strip out any hidden instructions or jailbreak text before my agent reads it."}],"resultDescription":"Returns a JSON object containing the sanitized version of the input text with any detected prompt injection or jailbreak payloads removed or flagged, along with metadata about what was detected.","failureModes":["Empty or missing 'text' field returns a 400 validation error","Very large payloads may time out or be rejected","Service unavailable (5xx) if the backend scanning engine is down","Payment required (402) if x402 micropayment is not provided or fails","False negatives: novel or highly obfuscated injection techniques may not be detected"],"whenToPreferThis":"Use this endpoint when your AI agent is consuming untrusted external content — scraped web pages, emails, third-party API responses, MCP tool outputs, or A2A agent payloads — and you need a dedicated firewall layer to detect and strip hidden prompt injections or jailbreak attempts before that content enters your LLM context. Prefer this over manual heuristics or generic text filtering when you need a purpose-built, actively maintained injection detection service that understands modern prompt attack vectors.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-21T06:47:54.153Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-cf120aa3"}