{"uid":"cap_seIBUPhZlao-e-3DJCVPJ","slug":"arxiv-digest-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-861d0dae","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://arxiv-digest.agentdiet.dev/v1/prompt-shield)","url":"https://arxiv-digest.agentdiet.dev/v1/prompt-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_z98IIOtHh_Q8Me77J9zlQ","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"arxiv-digest.agentdiet.dev","brandSlug":"arxiv-digest-agentdiet-dev-mpp","brandBaseUrl":"https://arxiv-digest.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Scans untrusted text, HTML, emails, MCP responses, or A2A payloads for hidden prompt injections and jailbreak attempts, returning sanitized output.","exampleAgentPrompt":"Before you process that scraped web page, run the raw HTML through the prompt-injection firewall first — I want to make sure there are no hidden instructions trying to hijack you.","exampleUseCases":[{"title":"Guard agent from malicious web content","prompt":"I'm building a research agent that scrapes news articles and summarizes them — can you scan each article's raw HTML through the prompt-injection firewall before feeding it to the summarizer, so embedded adversarial instructions don't hijack my agent?"},{"title":"Validate MCP tool responses before use","prompt":"My agent just got a response back from an external MCP tool. Before I let the agent act on it, can you run that payload through the jailbreak firewall to confirm there are no hidden prompt injections in it?"},{"title":"Screen inbound emails for prompt attacks","prompt":"I have an agent that reads and replies to customer emails — can you scan each incoming email body for hidden prompt-injection attempts before the agent processes them, so a malicious sender can't hijack its behavior?"}],"resultDescription":"Returns a structured object indicating whether a prompt injection or jailbreak was detected in the input text, along with sanitized/cleaned version of the content safe to pass downstream to an LLM or agent pipeline.","failureModes":["Empty or missing 'text' parameter returns a 400 validation error","Very large payloads may time out or be truncated","Highly obfuscated or novel injection techniques may evade detection (false negatives)","Non-UTF-8 or binary content may cause parsing failures","Rate limits or payment failures (HTTP 402) if USDC micropayment not supplied"],"whenToPreferThis":"Choose this endpoint when your AI agent pipeline ingests untrusted external content — scraped web pages, inbound emails, MCP tool responses, or A2A payloads — and you need a dedicated, purpose-built firewall to detect and strip hidden prompt injections before that content reaches your LLM. Prefer it over general-purpose content moderation APIs when the threat model is specifically adversarial prompt injection targeting agentic systems rather than harmful user-generated content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:27.209Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-63370fac"}