{"uid":"cap_YAKghNo_WrrqFogr6k7hp","slug":"mesh-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-firewall-f5333907","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://mesh.agentdiet.dev/v1/guard)","url":"https://mesh.agentdiet.dev/v1/guard?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_1KDbu896VoLiqsBlN6dpG","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"mesh.agentdiet.dev","brandSlug":"mesh-agentdiet-dev-mpp","brandBaseUrl":"https://mesh.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Scans untrusted text, HTML, emails, MCP responses, or A2A payloads for hidden prompt injection attacks and jailbreak attempts, returning sanitized output.","exampleAgentPrompt":"Before you process that scraped webpage, run the raw HTML through the prompt-injection firewall and give me back the sanitized version — I don't want any hidden instructions slipping into your context.","exampleUseCases":[{"title":"Sanitizing scraped web content for agents","prompt":"I need you to scan this raw HTML from that third-party website for any hidden prompt injections or jailbreak attempts before you summarize it for me — pass it through the firewall and show me the sanitized text."},{"title":"Guarding agent inbox from malicious emails","prompt":"Check this incoming email body for embedded prompt injection payloads or jailbreak instructions before my agent acts on it — I want to make sure nothing in there hijacks the AI's behavior."},{"title":"Validating MCP tool output in agent pipeline","prompt":"Before my agent uses this MCP server response, scan it for any indirect prompt injection attacks or adversarial instructions hidden in the payload and return a clean version I can safely pass downstream."}],"resultDescription":"Returns a JSON object containing the scan result for the submitted text, including whether prompt injection or jailbreak content was detected and a sanitized version of the input text safe for agent consumption.","failureModes":["Empty or missing 'text' field returns a validation error","Extremely large payloads may time out or be rejected","Payment not included or invalid x402 credentials returns a 402 Payment Required error","Malformed request body returns a 400 Bad Request","Service unavailable returns a 503 error"],"whenToPreferThis":"Choose this endpoint when your AI agent pipeline ingests content from untrusted external sources — scraped web pages, inbound emails, third-party API responses, MCP tool outputs, or A2A messages — and you need a dedicated, purpose-built firewall to detect and neutralize hidden prompt injection or jailbreak payloads before they reach your LLM context. Prefer this over generic content moderation APIs when the threat model is specifically adversarial instructions targeting AI agents rather than harmful user-facing content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:58.037Z","isFirstParty":false,"canonicalSlug":"mesh-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-firewall-3a18e5ba"}