{"uid":"cap_yJzOqrLlJlWHSB4p8x2yi","slug":"alpha-stream-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-8d24649e","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/llm-guard)","url":"https://alpha-stream.agentdiet.dev/v1/llm-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_Kj9TAO5HpNXaVtvSAnTUb","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, web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and jailbreak attempts, returning sanitized text.","exampleAgentPrompt":"Before processing this scraped web page content, run it through the prompt-injection firewall to detect and remove any hidden jailbreak instructions or indirect prompt injections: [paste untrusted HTML or text here].","exampleUseCases":[{"title":"Sanitize scraped web content for agent pipelines","prompt":"I'm building a research agent that scrapes web pages and feeds them to an LLM — can you scan this HTML from an untrusted site for hidden prompt injections before my agent processes it?"},{"title":"Check incoming email for jailbreak payloads","prompt":"Before my email-processing agent reads this customer email, scan it for any embedded jailbreak attempts or hidden prompt injection instructions that could hijack my agent's behavior."},{"title":"Validate MCP tool response before agent use","prompt":"My agent just got back a response from an external MCP tool — can you run it through the prompt-injection firewall to make sure there are no adversarial instructions hidden in the output before I pass it to the next step?"}],"resultDescription":"Returns an object containing the sanitized version of the input text with hidden prompt injections removed, along with detection signals indicating whether injection or jailbreak payloads were found in the original content.","failureModes":["Empty or too-short text input rejected (minLength:1 enforced)","Payment required error (HTTP 402) if x402 micropayment not provided","False negatives: novel or obfuscated injection patterns may not be detected","Overly aggressive sanitization may strip legitimate content","Timeout on very large HTML payloads","Idempotency-Key collision if same UUID reused across different inputs"],"whenToPreferThis":"Choose this endpoint when your AI agent pipeline ingests untrusted external content — web pages, emails, third-party API responses, or A2A payloads — and you need a dedicated firewall layer to detect and strip hidden prompt injections before that content reaches your LLM. Prefer it over generic content filters when the threat model specifically involves adversarial actors hiding instructions in data your agent will read.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:18.220Z","isFirstParty":false,"canonicalSlug":"alpha-stream-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-015b3890"}