{"uid":"cap_Fu47OyGjkLDIx9MSZwGyD","slug":"onchain-risk-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-69713d84","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/tool-poisoning-shield)","url":"https://onchain-risk.agentdiet.dev/v1/tool-poisoning-shield?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_d3VYpDDiGjJDUSqAaWWew","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 you summarize this scraped web page for me, run it through the prompt-injection firewall to check for any hidden jailbreak instructions embedded in the HTML: [paste content here].","exampleUseCases":[{"title":"Guarding agent from poisoned web pages","prompt":"I need you to scan this web page content I just scraped before you process it — check it for any hidden prompt injection or jailbreak payloads that might be trying to hijack you: [web page HTML here]."},{"title":"Screening inbound emails for LLM attacks","prompt":"Before you parse and action this customer email, run it through the prompt-injection firewall to make sure it doesn't contain any adversarial instructions trying to manipulate you: [email body here]."},{"title":"Validating MCP tool output before agent acts","prompt":"I got this response back from an external MCP tool — can you scan it for hidden prompt injections before we let the agent pipeline use it to make any decisions?"}],"resultDescription":"Returns a structured object containing the sanitized version of the submitted text with any detected prompt injection or jailbreak payloads removed or flagged, along with detection metadata indicating whether malicious content was found.","failureModes":["Empty or missing 'text' field returns a 400 validation error","Payload too large may result in timeout or truncation","False negatives possible for novel or obfuscated injection techniques","402 Payment Required if x402 micropayment header is absent or invalid","Network timeout if the service is temporarily unavailable"],"whenToPreferThis":"Choose this endpoint when your agent pipeline ingests untrusted external content — web pages, emails, tool outputs, or third-party API responses — before passing that content to an LLM for reasoning or action. It is specifically designed for the indirect prompt injection threat model where adversarial text is embedded in data sources the agent consumes, not direct user input.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-21T00:36:38.091Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-cf120aa3"}