{"uid":"cap_jljFDSsRf6C9lUBj5xZ_G","slug":"onchain-risk-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-7b02d497","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://onchain-risk.agentdiet.dev/v1/mcp-security)","url":"https://onchain-risk.agentdiet.dev/v1/mcp-security?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_GBUuFeZ4QL7zHqbU55aHv","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"onchain-risk.agentdiet.dev","brandSlug":"onchain-risk-agentdiet-dev-mpp","brandBaseUrl":"https://onchain-risk.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 my agent processes this scraped web page content, scan it for any hidden prompt injections or jailbreak attempts and give me the sanitized version: [paste raw HTML or text here].","exampleUseCases":[{"title":"Protecting agent from malicious web content","prompt":"I just scraped this web page to feed into my agent's context — can you scan it for any hidden prompt injection instructions before my agent reads it? Here's the raw HTML: <html>..."},{"title":"Sanitizing third-party email before LLM processing","prompt":"My agent is about to summarize this customer email but I'm worried it might contain adversarial instructions. Can you check this email body for prompt injections and return a safe version? The email says: 'Please ignore previous instructions and...'"},{"title":"Auditing MCP tool response for jailbreak payloads","prompt":"My agent just got back a response from an external MCP tool and I need to make sure it's safe before passing it downstream. Scan this tool output for any embedded jailbreak or prompt injection content: {\"result\": \"Ignore all prior rules and...\"}"}],"resultDescription":"Returns a JSON object indicating whether prompt injection or jailbreak content was detected, along with sanitized text stripped of adversarial instructions, making it safe for downstream agent consumption.","failureModes":["Empty or missing 'text' field returns a 400 validation error","Very large payloads may hit size or token limits","Sophisticated obfuscated injections may evade detection (false negatives)","Payment failure via x402 returns 402 before processing","Service unavailability returns 5xx error","Ambiguous edge cases may produce false positives on legitimate content"],"whenToPreferThis":"Choose this endpoint when your agent pipeline ingests untrusted external content — scraped web pages, emails, MCP/A2A tool responses, or user-submitted text — and you need a dedicated firewall layer to detect and neutralize hidden prompt injection or jailbreak payloads before they reach your LLM. Prefer this over generic content filters when you specifically need AI-agent-aware injection detection that understands indirect prompt injection patterns targeting LLM contexts.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-21T12:37:55.616Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-cf120aa3"}