{"uid":"cap_R7dcqV1CvkN5HUIEvZEv_","slug":"arxiv-digest-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-3bc9cb74","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/indirect-injection-guard)","url":"https://arxiv-digest.agentdiet.dev/v1/indirect-injection-guard?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_f7gVx5MJXBgTbboz5xQ5w","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 a sanitized result.","exampleAgentPrompt":"Before you process this scraped web page content, run it through the prompt-injection firewall to check for any hidden jailbreak instructions or embedded adversarial prompts: '<html>...page content here...</html>'","exampleUseCases":[{"title":"Sanitize scraped web content for agent","prompt":"I'm building an agent that scrapes news articles and summarizes them — before passing each page's HTML to the LLM, scan it for hidden prompt injections so malicious sites can't hijack my agent's behavior."},{"title":"Guard against malicious MCP tool responses","prompt":"My agent just got a response from an external MCP tool and I want to make sure it doesn't contain any embedded jailbreak instructions before I let the agent act on it — can you scan this tool output for prompt injection?"},{"title":"Check user-submitted email for adversarial prompts","prompt":"A user forwarded me this email to summarize, but I'm worried it might contain invisible prompt injection tricks targeting my AI assistant — please scan the email body for any hidden adversarial instructions before I process it."}],"resultDescription":"Returns an object indicating whether prompt injection or jailbreak content was detected in the input text, along with sanitized text with the malicious instructions removed or flagged, enabling safe downstream processing by an AI agent.","failureModes":["Empty or missing 'text' parameter returns a validation error","Very long inputs may hit size or timeout limits","Novel or obfuscated injection techniques may evade detection","Non-UTF-8 or binary input may cause parse errors","Service unavailability returns a 402 or 5xx error"],"whenToPreferThis":"Choose this endpoint when your AI agent is ingesting content from untrusted external sources — web scraping, user-submitted emails, third-party MCP or A2A tool responses — and you need an automated security layer to detect and neutralize hidden prompt injection or jailbreak payloads before they reach your LLM. Especially valuable in autonomous agent pipelines where adversarial content could redirect agent behavior without human oversight.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:06.671Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-63370fac"}