{"uid":"cap_mY1ImtqpeF2Rem8pTcwEF","slug":"agentdiet-prompt-shield-732fae9f","name":"AgentDiet Prompt Shield","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://agentdiet.dev/v1/prompt-shield)","url":"https://agentdiet.dev/v1/prompt-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":["x402"],"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":"unknown","protocol":"x402","network":"base","amountUsd":null,"per":"call","confidence":"unknown"},{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_AbMvLLggnBD1V6Pgk7cNY","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null},{"uid":"pm_DcvAl1iNgRr5P84qUjxyy","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Scans untrusted text (web pages, emails, MCP responses, A2A payloads) for hidden prompt injections and jailbreak attempts, returning sanitized content.","exampleAgentPrompt":"Before you process that webpage I just scraped, run it through the prompt shield first — check the text for any hidden prompt injections or jailbreak instructions that could hijack you.","exampleUseCases":[{"title":"Safe web scraping for agent pipelines","prompt":"I'm about to feed this scraped article into my research agent — can you scan the raw text first to make sure there are no hidden prompt injection attacks embedded in it?"},{"title":"Email body safety check before summarization","prompt":"Before you summarize this email from an unknown sender, please run the body text through a prompt injection firewall to make sure it's not trying to manipulate you."},{"title":"MCP response sanitization before tool use","prompt":"My agent just got a response from an external MCP server — can you check that response text for any adversarial instructions or jailbreak payloads before I let the agent act on it?"}],"resultDescription":"Returns a sanitized version of the input text with prompt injection payloads removed or flagged, along with detection verdicts indicating whether hidden adversarial instructions or jailbreak attempts were found.","failureModes":["Empty or missing 'text' query parameter returns an error","Extremely large payloads may be rejected or truncated","Sophisticated obfuscated injections may evade detection","Non-text or binary content passed as text may cause unexpected behavior","Network timeout on very large inputs"],"whenToPreferThis":"Use this endpoint when your agent pipeline ingests content from untrusted external sources — scraped web pages, user-submitted emails, third-party MCP responses, or A2A payloads — and you need a dedicated firewall layer to detect and strip hidden prompt injections before that content reaches your LLM. Prefer this over generic content filtering when the threat model specifically involves adversarial AI manipulation rather than general content moderation.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T12:48:20.193Z","isFirstParty":false,"canonicalSlug":"agentdiet-prompt-shield-732fae9f"}