{"uid":"cap_Zm9t-UJ1C28w_EoaULsKX","slug":"prompt-guard-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-676f3506","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://prompt-guard.agentdiet.dev/v1/system-prompt-guard)","url":"https://prompt-guard.agentdiet.dev/v1/system-prompt-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_MZ_UBmrlv4F3P0RWA3RH9","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"prompt-guard.agentdiet.dev","brandSlug":"prompt-guard-agentdiet-dev-mpp","brandBaseUrl":"https://prompt-guard.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Scans untrusted text, HTML, emails, MCP responses, or A2A payloads for hidden prompt injections and jailbreak attempts, returning sanitized output.","exampleAgentPrompt":"Before you summarize that webpage I just fetched, run the raw HTML through the prompt-injection firewall to check for any hidden instructions trying to hijack you, and give me the sanitized version to work with.","exampleUseCases":[{"title":"Guarding agent from malicious webpages","prompt":"I need you to scan the raw HTML content of this webpage before processing it — check it for any hidden prompt injections or jailbreak payloads that might try to manipulate you: [raw HTML here]."},{"title":"Sanitizing inbound email before LLM processing","prompt":"Before you summarize this customer email for me, run it through the prompt-injection firewall — I want to make sure there are no embedded instructions trying to hijack your behavior: [email text here]."},{"title":"Validating MCP tool response before agent acts","prompt":"This MCP tool just returned a response and I want you to scan it for any adversarial prompt injections before you use it to take any actions — here's the raw response payload: [payload here]."}],"resultDescription":"Returns a JSON object indicating whether prompt injection or jailbreak content was detected in the input, along with sanitized text safe for downstream LLM or agent processing.","failureModes":["Empty or missing 'text' field returns a 400 validation error","Payment not provided or invalid returns HTTP 402 with x402 payment challenge","Very large payloads may exceed size limits and return a 413 error","Obfuscated or novel injection techniques may not be detected (false negatives)","Network timeouts on the remote endpoint return connection errors"],"whenToPreferThis":"Choose this endpoint when your agent pipeline ingests content from untrusted external sources — scraped web pages, user-submitted emails, third-party API responses, MCP tool outputs, or A2A messages — and you need a dedicated firewall layer before passing that content to an LLM or triggering downstream actions. Prefer it over generic content filters when your threat model specifically includes indirect prompt injection and jailbreak payloads targeting agentic systems.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:13.420Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-3e4a7f21"}