{"uid":"cap_Q8wtaQ_QFfGdVV2S_yKJP","slug":"agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-firewall-910dcde5","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://agentdiet.dev/v1/jailbreak-scan)","url":"https://agentdiet.dev/v1/jailbreak-scan?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_K2bj87dPNDvY0SvOzq5Re","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"agentdiet.dev","brandSlug":"agentdiet-dev-mpp","brandBaseUrl":"https://agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Scans untrusted text, HTML, emails, MCP responses, or A2A payloads for hidden prompt injection and jailbreak attempts, returning sanitized output.","exampleAgentPrompt":"Before you process that scraped webpage, can you run it through the jailbreak firewall to check for any hidden prompt injections or adversarial instructions embedded in the HTML?","exampleUseCases":[{"title":"Sanitizing scraped web content for agents","prompt":"I'm about to feed this scraped article into my agent pipeline — can you first scan the raw HTML for any hidden prompt injections or jailbreak payloads embedded in the page before the agent reads it?"},{"title":"Filtering untrusted email before processing","prompt":"This email came from an unknown sender and my agent is about to summarize it — please scan the email body for any indirect prompt injection attempts or adversarial instructions trying to hijack the agent."},{"title":"Validating MCP tool output before agent use","prompt":"My agent just got a response back from an external MCP tool and I don't fully trust the source — can you run that tool output through the prompt injection firewall to make sure it's safe to pass along to the next step in my workflow?"}],"resultDescription":"Returns a JSON object indicating whether prompt injection or jailbreak content was detected in the input text, along with a sanitized version of the text safe for downstream agent consumption.","failureModes":["Missing required 'text' parameter returns a 400 bad request error","Empty string input rejected due to minLength:1 constraint","Very large payloads may time out or be truncated","Payment failure via x402 returns HTTP 402 and blocks the scan","Ambiguous or encoded injections may be missed if obfuscation is novel","Non-UTF-8 or binary content may cause parsing errors"],"whenToPreferThis":"Choose this endpoint when your AI agent is about to ingest content from untrusted external sources — scraped web pages, third-party emails, external MCP/A2A tool responses, or user-supplied text — and you need a lightweight firewall pass before the content influences agent behavior. It is specifically designed for the A2A and MCP agent security use case, making it more appropriate than generic content moderation APIs when the threat model is adversarial prompt injection rather than hate speech or NSFW content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:23.133Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-firewall-fbd96f9b"}