{"uid":"cap_32Upcg6TD9HEeFGb-xUVz","slug":"defi-yield-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-5076ff8e","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://defi-yield.agentdiet.dev/v1/rag-poison-shield)","url":"https://defi-yield.agentdiet.dev/v1/rag-poison-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_RWBWyYVe_B7H9HWURZT2O","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"defi-yield.agentdiet.dev","brandSlug":"defi-yield-agentdiet-dev-mpp","brandBaseUrl":"https://defi-yield.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Scans untrusted text, HTML, emails, MCP responses, or A2A payloads for hidden prompt-injection and jailbreak attacks, returning sanitized output.","exampleAgentPrompt":"Before I pass this scraped webpage content into our RAG pipeline, scan it for any hidden prompt injections or jailbreak payloads and give me the sanitized version: [paste untrusted text here].","exampleUseCases":[{"title":"RAG pipeline poisoning defense","prompt":"I'm about to ingest this batch of web-scraped documents into my vector store — can you scan each one for hidden prompt-injection instructions before I add them to the RAG index? Here's the first one: [document text]."},{"title":"Email body jailbreak check","prompt":"I just received this email that my agent is going to process automatically — can you check whether it contains any prompt-injection or jailbreak payloads hidden in the text before my agent acts on it?"},{"title":"MCP tool output sanitization","prompt":"My agent just got back this response from an external MCP tool call and I don't trust the source — scan it for indirect prompt injection and return me a clean version I can safely feed into the next step of the pipeline."}],"resultDescription":"Returns a JSON object containing the sanitized version of the input text with any detected prompt-injection or jailbreak payloads removed or neutralized, along with detection signals indicating whether malicious content was found.","failureModes":["Empty or missing 'text' parameter returns a validation error","Extremely long inputs may be truncated or rejected","Highly obfuscated injections using novel encodings may evade detection","Payment failure (HTTP 402) if x402 USDC micropayment is not completed","Network timeout for very large HTML payloads","False positives on legitimate instructional text that resembles injection syntax"],"whenToPreferThis":"Choose this endpoint when your AI agent pipeline ingests content from untrusted external sources — web scraping, emails, third-party MCP tool responses, or user-submitted text — and you need a dedicated firewall layer to catch indirect prompt-injection and jailbreak attempts before that content reaches your LLM. Prefer this over generic content moderation APIs when the threat model is specifically adversarial AI manipulation rather than hate speech or NSFW content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:42.622Z","isFirstParty":false,"canonicalSlug":"defi-yield-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-76aae4ab"}