{"uid":"cap_UUbCfTkd356ZvyzUXqI-T","slug":"email-verify-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-cb4d5385","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://email-verify.agentdiet.dev/v1/mcp-security)","url":"https://email-verify.agentdiet.dev/v1/mcp-security?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"},"limit":{"type":"integer","default":20,"maximum":100,"minimum":1,"description":"Maximum number of items to return per page (1-100)"},"cursor":{"type":"string","description":"Opaque pagination cursor for fetching the next page"}}},"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_coXvz0QVTI4k-Bhas1mQM","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"email-verify.agentdiet.dev","brandSlug":"email-verify-agentdiet-dev-mpp","brandBaseUrl":"https://email-verify.agentdiet.dev","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 process that scraped web page, can you scan it for any hidden prompt injection or jailbreak instructions and give me back the sanitized text?","exampleUseCases":[{"title":"Sanitizing scraped web pages for LLM pipelines","prompt":"I'm about to feed this web page content to my LLM — can you first scan it for any hidden prompt injections or jailbreak payloads and return the safe, sanitized version?"},{"title":"Protecting agent from malicious email content","prompt":"Before my agent reads this email body, scan it for any embedded prompt injection attacks or hidden instructions trying to hijack my AI, and let me know if anything suspicious was found."},{"title":"Validating MCP tool responses before processing","prompt":"My agent just got a response back from an external MCP tool — can you check this payload for any indirect prompt injection attempts before I let the agent act on it?"}],"resultDescription":"A structured response containing detection results for prompt injection and jailbreak patterns found in the submitted text, along with a sanitized version of the input with malicious instructions removed or flagged.","failureModes":["Missing required 'text' parameter returns a validation error","Empty string input rejected due to minLength:1 constraint","Extremely large payloads may timeout or be truncated","Ambiguous or sophisticated obfuscated injections may go undetected","Service unavailability returns HTTP 402 or 5xx errors","Pagination cursor mismatch returns empty or incorrect result pages"],"whenToPreferThis":"Choose this endpoint when your AI agent pipeline consumes untrusted external content — scraped web pages, emails, MCP/A2A tool responses, or user-submitted text — and you need to detect and neutralize indirect prompt injection or jailbreak attempts before they reach your LLM. It is especially appropriate in agentic workflows where tool outputs feed back into a reasoning loop, making them a prime attack surface. Prefer this over generic content moderation APIs when the specific threat model is prompt injection rather than hate speech or NSFW content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-21T12:37:09.101Z","isFirstParty":false,"canonicalSlug":"email-verify-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-dd577fbf"}