{"uid":"cap_91uJ7R7qSRTJZ6ad9Dwc_","slug":"json-repair-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-c55acbdf","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://json-repair.agentdiet.dev/v1/system-prompt-guard)","url":"https://json-repair.agentdiet.dev/v1/system-prompt-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_LTFYVzBcZtI_AgJhzx8tk","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"json-repair.agentdiet.dev","brandSlug":"json-repair-agentdiet-dev-mpp","brandBaseUrl":"https://json-repair.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 web page I just scraped, run it through the prompt injection firewall to check for any hidden instructions or jailbreak payloads embedded in the HTML, and give me the sanitized version.","exampleUseCases":[{"title":"Safe web scraping for agent pipeline","prompt":"I'm having my agent scrape competitor websites and feed the content into a downstream LLM — can you scan this raw HTML from the page before passing it along, to make sure there are no hidden prompt injections trying to hijack the agent?"},{"title":"Email body threat screening","prompt":"This email came in from an external sender and I want to process it with my AI assistant — first, scan the full email body for any embedded jailbreak instructions or indirect prompt injection attempts so I know it's safe to hand off."},{"title":"MCP tool response validation","prompt":"My agent just got back a response from an external MCP tool and I'm not sure I trust it — can you run it through the prompt injection firewall to detect and strip any adversarial payloads before I let my agent act on it?"}],"resultDescription":"Returns a structured JSON object containing the sanitized version of the input text with any detected prompt injection or jailbreak payloads identified and removed or flagged, along with threat detection metadata.","failureModes":["Empty or missing 'text' parameter returns a validation error","Extremely long input text may be truncated or rejected","Obfuscated or novel injection techniques may not be detected","Payment failure via x402 returns HTTP 402 before processing","Ambiguous content with no clear injection signals may pass through without flagging"],"whenToPreferThis":"Choose this endpoint when your AI agent pipeline ingests content from untrusted external sources — scraped web pages, user-submitted text, third-party API/MCP responses, or A2A payloads — and you need to validate that content is safe before passing it to an LLM. Particularly valuable in multi-agent orchestration scenarios where one agent's output becomes another's input, creating injection attack surfaces.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:38:27.966Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-6acbd45e"}