{"uid":"cap_CaRS3eAIVK13gY8f8o5xl","slug":"alpha-stream-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-318b2901","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://alpha-stream.agentdiet.dev/v1/guard)","url":"https://alpha-stream.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_1zKuKixwP6mim6gVcI5Me","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"alpha-stream.agentdiet.dev","brandSlug":"alpha-stream-agentdiet-dev-mpp","brandBaseUrl":"https://alpha-stream.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 this scraped webpage content, run it through the prompt injection firewall to check for any hidden jailbreak instructions and give me the sanitized version: [paste raw HTML or text here].","exampleUseCases":[{"title":"Sanitizing web scrape before LLM ingestion","prompt":"I just scraped this product review page and want to feed it to my summarization agent — can you scan this HTML for any hidden prompt injections first and give me the clean text? Here's the raw content: [HTML blob]."},{"title":"Guarding agent from malicious email content","prompt":"My agent is about to read this forwarded email to extract action items, but I'm worried it might contain adversarial instructions. Can you scan this email body for prompt injection or jailbreak payloads before my agent processes it?"},{"title":"Validating MCP tool output for agent pipelines","prompt":"My MCP tool just returned this response from an external data source — before I pass it to the next step in my agent pipeline, please check it for hidden prompt injections or jailbreak attempts and return a sanitized version."}],"resultDescription":"Returns a JSON object containing the scan result for the submitted text, including detection of any hidden prompt injection or jailbreak payloads and a sanitized version of the content safe for downstream LLM consumption.","failureModes":["Empty or missing 'text' field returns a 400 validation error","Payment not provided or insufficient funds returns HTTP 402 requiring x402 USDC payment","Very long payloads may be truncated or rejected depending on service limits","Highly obfuscated injections using encoding tricks may evade detection","Service unavailability returns 5xx errors; idempotency key can be used to safely retry"],"whenToPreferThis":"Choose this endpoint when your AI agent pipeline ingests content from untrusted external sources — scraped web pages, user-submitted emails, third-party API or MCP tool responses, or A2A payloads — and you need to ensure that content does not contain adversarial prompt injection or jailbreak instructions before passing it to an LLM. Prefer it over generic content filters when the specific threat model is AI prompt manipulation rather than spam or NSFW content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-21T06:44:00.184Z","isFirstParty":false,"canonicalSlug":"alpha-stream-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-015b3890"}