{"uid":"cap_DX9cEZfI00V0Run-_8eK4","slug":"arxiv-digest-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-8c1c4eb0","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://arxiv-digest.agentdiet.dev/v1/tool-poisoning-shield)","url":"https://arxiv-digest.agentdiet.dev/v1/tool-poisoning-shield?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_EUZRZpyv1rmx8-FXjwj66","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"arxiv-digest.agentdiet.dev","brandSlug":"arxiv-digest-agentdiet-dev-mpp","brandBaseUrl":"https://arxiv-digest.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 that scraped webpage, run it through the prompt-injection firewall first — the raw HTML might contain hidden instructions trying to hijack you, so scan it and give me the sanitized version.","exampleUseCases":[{"title":"Safe web scraping for agent pipelines","prompt":"I just scraped this webpage to feed into my research agent, but I'm worried it might contain hidden prompt injections — can you scan the raw HTML for any jailbreak payloads and give me the sanitized text?"},{"title":"Email safety check before agent reads","prompt":"My AI assistant is about to read and summarize this customer email, but it looks suspicious — run it through the prompt-injection firewall to make sure it's not trying to manipulate my agent before forwarding it."},{"title":"Validating MCP tool response before use","prompt":"My agent just got a response back from an external MCP tool and I don't fully trust the source — scan that tool output for any hidden prompt injections or jailbreak attempts before my agent acts on it."}],"resultDescription":"Returns a JSON object containing the sanitized version of the input text with any detected prompt injection payloads removed or flagged, along with indicators of what (if any) malicious instructions were found embedded in the original content.","failureModes":["Empty or missing 'text' parameter returns a validation error","Extremely large payloads may timeout or be truncated","False negatives: novel or obfuscated injection techniques may not be detected","False positives: legitimate instructions in the text may be incorrectly flagged as injections","Service unavailable if the upstream API is down or payment (x402) fails"],"whenToPreferThis":"Choose this endpoint when your AI agent needs to safely process content from untrusted external sources — such as web scrapes, external tool responses, MCP payloads, emails, or user-submitted text — before passing that content into an LLM context where hidden instructions could hijack agent behavior. Prefer this over generic content filtering when the threat model is specifically indirect prompt injection or jailbreak via data channels in agentic pipelines.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:17.026Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-63370fac"}