{"uid":"cap_XIPWIzNEAzqJgxBjk54jr","slug":"broker-prompt-shield-0c05e245","name":"broker-prompt-shield","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://x402broker.com/v1/prompt-shield)","url":"https://x402broker.com/v1/prompt-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":["x402"],"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":"unknown","protocol":"x402","network":"base","amountUsd":null,"per":"call","confidence":"unknown"},{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_yYyLCFzkhRHNFbS2KezIi","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null},{"uid":"pm_zUrAZ5AO8ziOxIxh-y_Zi","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Scans untrusted text (web pages, emails, MCP responses, A2A payloads) for hidden prompt injections and jailbreak attempts, returning sanitized content safe for agent consumption.","exampleAgentPrompt":"Before you process that web page I just scraped, run it through the prompt-shield firewall to check for any hidden prompt injections or jailbreak instructions embedded in the content.","exampleUseCases":[{"title":"Guard agent before processing scraped page","prompt":"I'm about to have my agent summarize this webpage, but I don't trust it — can you scan the raw HTML text through prompt-shield first to make sure there are no hidden instructions trying to hijack the agent?"},{"title":"Screen incoming email for jailbreak payloads","prompt":"My agent reads customer emails and auto-responds. Before it processes this new email, run the body text through the prompt injection firewall to make sure it doesn't contain any adversarial instructions."},{"title":"Sanitize third-party MCP tool response","prompt":"My agent just got a response back from an external MCP tool. Can you pass that response through the prompt-shield scanner and give me the sanitized version before I let the agent act on it?"}],"resultDescription":"Returns sanitized text with hidden prompt injections and jailbreak attempts removed or neutralized, along with detection signals indicating whether adversarial content was found in the input.","failureModes":["Missing or empty 'text' query parameter returns a validation error","Overly long input text may be truncated or rejected","Novel obfuscation techniques may evade detection (false negative)","Benign instructional content may be flagged as injection (false positive)","Payment failure or insufficient USDC balance blocks the request"],"whenToPreferThis":"Choose this endpoint when your agent pipeline ingests content from untrusted external sources — scraped web pages, user emails, third-party API responses, or A2A payloads — and you need to sanitize that content before an LLM processes it. It is specifically designed for agentic and multi-agent architectures where indirect prompt injection is a real attack vector, distinguishing it from generic content moderation APIs.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T12:48:15.655Z","isFirstParty":false,"canonicalSlug":"broker-prompt-shield-0c05e245"}