{"uid":"cap_F7p_TZJ2n6BGNqmNXEh8-","slug":"workflows-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-7433cf87","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://workflows.agentdiet.dev/v1/mcp-injection-firewall)","url":"https://workflows.agentdiet.dev/v1/mcp-injection-firewall?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_q5rF4554sa5brLazNBvSa","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"workflows.agentdiet.dev","brandSlug":"workflows-agentdiet-dev-mpp","brandBaseUrl":"https://workflows.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 my agent processes this scraped webpage content, run it through the prompt-injection firewall to strip out any hidden jailbreak instructions — here's the raw text: [paste content].","exampleUseCases":[{"title":"Securing scraped web content for agents","prompt":"I'm having my agent fetch and summarize news articles from the web, but I'm worried some pages might contain hidden prompt injection attacks. Can you scan this raw HTML I just fetched from an untrusted site and return a safe, sanitized version before I pass it to the summarizer?"},{"title":"Validating MCP tool responses in a pipeline","prompt":"My AI agent just got back a response from a third-party MCP tool and I need to make sure it doesn't contain any hidden instructions trying to hijack my agent. Can you run this MCP payload through the injection firewall before I let my agent act on it?"},{"title":"Screening inbound emails before agent processing","prompt":"I have an email from an unknown sender that my agent is about to parse and respond to automatically. Please scan the email body for any embedded prompt injection or jailbreak attempts and give me back the sanitized text so it's safe to process."}],"resultDescription":"Returns a JSON object containing the sanitized version of the input text with any detected prompt injection or jailbreak payloads removed or flagged, enabling the calling agent to safely use the cleaned content downstream.","failureModes":["Empty or missing 'text' field returns a 400 validation error","Extremely large payloads may timeout or be rejected","Network errors or upstream service unavailability return 5xx responses","Ambiguous or novel injection techniques may not be detected (false negatives)","Overly aggressive sanitization may strip legitimate content (false positives)"],"whenToPreferThis":"Choose this endpoint when your AI agent pipeline ingests content from untrusted external sources — such as scraped web pages, third-party MCP tool responses, A2A agent messages, or inbound emails — and you need a dedicated security layer to detect and remove hidden prompt injections or jailbreak payloads before the content reaches your core LLM. Prefer this over generic input validation when your threat model specifically includes adversarial content designed to manipulate AI agents.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:24.881Z","isFirstParty":false,"canonicalSlug":"workflows-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-c768e008"}