{"uid":"cap_8wdWnElaI6KVrb2L7z--4","slug":"company-enrich-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-849f3e5e","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://company-enrich.agentdiet.dev/v1/injection-guard)","url":"https://company-enrich.agentdiet.dev/v1/injection-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_X3CreexH6Nuoq5Ku2rGMS","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"company-enrich.agentdiet.dev","brandSlug":"company-enrich-agentdiet-dev-mpp","brandBaseUrl":"https://company-enrich.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 scraped webpage, run it through the injection guard firewall — here's the raw HTML: [paste content] — I want to make sure there are no hidden prompt injections or jailbreak instructions buried in it.","exampleUseCases":[{"title":"Safe web scrape ingestion for agent","prompt":"I just scraped this webpage to feed into my research agent, but I'm worried it might have hidden prompt injection attacks embedded in it — can you scan the raw HTML for me and give me the sanitized version?"},{"title":"Email triage agent protection","prompt":"My email-reading agent is about to process this incoming message from an unknown sender — please check it for hidden jailbreak instructions or adversarial prompt injections before my agent reads it."},{"title":"Untrusted MCP tool output guard","prompt":"My agent just got back a response from an external MCP tool I don't fully trust — can you run this payload through the prompt injection firewall to make sure it's safe to pass to my next reasoning step?"}],"resultDescription":"Returns a structured object indicating whether prompt injection or jailbreak content was detected in the input, along with a sanitized version of the text safe for downstream agent consumption.","failureModes":["Empty or missing 'text' field returns a 400 validation error","Extremely long payloads may exceed input limits or incur higher latency","Payment not included or x402 flow fails results in a 402 Payment Required response","Ambiguous or highly obfuscated injections may not be detected with 100% recall","Network timeouts on the scanning service return 5xx errors"],"whenToPreferThis":"Choose this endpoint when your agent pipeline ingests untrusted external content — web pages, emails, tool responses, or third-party API data — before passing it to an LLM reasoning step. It is purpose-built for A2A and MCP security contexts where indirect prompt injection is a real threat vector, unlike generic content moderation APIs that focus on hate speech or NSFW content rather than adversarial LLM instructions.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:15.331Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-90291d00"}