{"uid":"cap_1uXz_pFqja7RNROOBLCRd","slug":"polymarket-odds-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-5cf7f1d8","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://polymarket-odds.agentdiet.dev/v1/system-prompt-guard)","url":"https://polymarket-odds.agentdiet.dev/v1/system-prompt-guard?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_GBbOK0UzQsmPQ2j-H_KOh","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"polymarket-odds.agentdiet.dev","brandSlug":"polymarket-odds-agentdiet-dev-mpp","brandBaseUrl":"https://polymarket-odds.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Scans untrusted text, HTML, emails, MCP responses, or A2A payloads for hidden prompt injections and jailbreak attempts, returning sanitized content.","exampleAgentPrompt":"Before you summarize that scraped webpage, run the raw HTML through the prompt injection firewall first — I want to make sure there are no hidden instructions trying to hijack you embedded in the page content.","exampleUseCases":[{"title":"Safe web scraping pipeline","prompt":"I'm building an agent that summarizes news articles from arbitrary URLs — can you scan the raw HTML of each page for hidden prompt injections before passing it to the summarizer?"},{"title":"Email safety check for agent inbox","prompt":"My agent reads and acts on incoming emails — before it processes this email body, check it for any embedded jailbreak payloads or hidden instructions trying to override its behavior."},{"title":"MCP tool output sanitization","prompt":"This MCP server returned some text that I want to feed into my next agent step — can you run it through the prompt injection firewall to strip out any adversarial content before I use it?"}],"resultDescription":"Returns a structured object indicating whether prompt injection or jailbreak content was detected in the input text, along with sanitized output that has had malicious instructions removed or neutralized, enabling safe downstream processing by AI agents.","failureModes":["Empty or missing 'text' parameter returns a validation error","Extremely large payloads may be rejected or truncated","False negatives possible if injections use novel obfuscation techniques","False positives may flag legitimate system-style instructions in benign content","HTTP 402 returned if payment is missing or insufficient (x402 micropayment required)","Service unavailability returns a 5xx error"],"whenToPreferThis":"Choose this endpoint when your AI agent processes content from untrusted external sources — scraped web pages, user-submitted emails, third-party MCP or A2A tool responses — and you need a dedicated firewall check before feeding that content into your LLM pipeline. It is particularly valuable in multi-agent architectures where one agent's output becomes another's input and indirect prompt injection is a real attack vector.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:49:14.747Z","isFirstParty":false,"canonicalSlug":"polymarket-odds-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-8ce8b4f9"}