{"uid":"cap_BQkmv0PVuWyQyn0GmNUmP","slug":"preflight-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-a00011ca","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://preflight.agentdiet.dev/v1/injection-guard)","url":"https://preflight.agentdiet.dev/v1/injection-guard?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_W0BMSstjKke9YYVB6qlaF","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"preflight.agentdiet.dev","brandSlug":"preflight-agentdiet-dev-mpp","brandBaseUrl":"https://preflight.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 output.","exampleAgentPrompt":"Before my agent processes this scraped webpage content, can you run it through the injection-guard firewall to detect any hidden prompt injections or jailbreak payloads and give me back the sanitized version? Here's the text: [paste untrusted content]","exampleUseCases":[{"title":"Sanitize scraped web content before agent ingestion","prompt":"I'm about to feed this scraped article into my AI pipeline — can you first scan it for any hidden prompt injections or jailbreak instructions embedded in the HTML and return me only the clean, safe text?"},{"title":"Guard agent inbox from malicious email payloads","prompt":"My AI assistant is reading incoming emails automatically. Before it processes this email body, please check it for indirect prompt injection attacks or hidden jailbreak commands and sanitize it."},{"title":"Validate MCP tool response before chaining","prompt":"My orchestration agent just got back a response from an external MCP tool. Can you run the injection-guard scan on this payload to make sure there are no hidden instructions trying to hijack my agent before I pass it downstream?"}],"resultDescription":"Returns a structured object indicating whether prompt injection or jailbreak content was detected in the input, along with sanitized text safe for downstream agent consumption. Likely includes a detection flag, risk classification, and cleaned version of the input.","failureModes":["Empty or missing 'text' parameter returns a validation error","Extremely long payloads may be truncated or rejected","Network timeout on large HTML documents","False negatives on novel or obfuscated injection patterns","Non-UTF-8 encoded content may cause parsing errors"],"whenToPreferThis":"Choose this endpoint when your agent needs to safely consume content from untrusted external sources — web scrapes, emails, third-party API or MCP tool responses, or A2A payloads — before feeding them into an LLM context window. It is specifically designed for the agentic security use case of indirect prompt injection and jailbreak detection, making it ideal for multi-agent pipelines, autonomous browsing agents, and orchestrators that must process untrusted data at runtime.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:25.743Z","isFirstParty":false,"canonicalSlug":"preflight-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-5b5b7e27"}