{"uid":"cap_q0Weg_aj7gUu8iIXoWQ5_","slug":"json-repair-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-c305dc78","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/llm-guard)","url":"https://json-repair.agentdiet.dev/v1/llm-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_4IhBvUnGDq41V4ZKGrN9H","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 injections and jailbreak attempts, returning sanitized output.","exampleAgentPrompt":"Before you process this web page I just scraped, run it through the prompt injection firewall to check for any hidden jailbreak instructions or adversarial prompt injections embedded in the content.","exampleUseCases":[{"title":"Securing agent web scraping pipeline","prompt":"I'm having my agent scrape product review pages and feed them to an LLM — can you scan each page's HTML through the prompt injection firewall before my agent reads it, so I don't get hijacked by anything malicious embedded in the content?"},{"title":"Validating MCP tool responses","prompt":"My agent just got back a response from an external MCP tool and I want to make sure it doesn't contain any hidden prompt injections or jailbreak payloads — can you run it through the LLM-Guard firewall before I let my agent act on it?"},{"title":"Screening inbound email for LLM processing","prompt":"I'm building an email-to-agent workflow and I need you to scan this inbound customer email for any hidden prompt injection attempts before passing it to the summarization LLM — check it for jailbreak payloads and return a sanitized version."}],"resultDescription":"A JSON object containing the scan result for the submitted text, indicating whether prompt injections or jailbreak payloads were detected, along with sanitized text safe for downstream LLM consumption.","failureModes":["Empty or missing 'text' field returns a 400 validation error","Extremely long payloads may hit size limits or timeout","Ambiguous or borderline content may produce false positives or false negatives","Network errors or payment failures (402) if x402 micropayment is not handled","Malformed request body returns schema validation error"],"whenToPreferThis":"Choose this endpoint when your AI agent pipeline ingests content from untrusted external sources — web scrapes, emails, third-party MCP or A2A tool responses — and you need to sanitize that content before passing it to an LLM. It is especially valuable in agentic pipelines where indirect prompt injection is a real attack vector and you want a dedicated firewall layer rather than relying solely on your LLM's own guardrails.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:34.079Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-6acbd45e"}