{"uid":"cap_LCg36gVvXmQ6uxwQuVSqE","slug":"token-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-680b8d3d","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://token-intel.agentdiet.dev/v1/prompt-shield)","url":"https://token-intel.agentdiet.dev/v1/prompt-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_vj3v-83qdflpuuj2u-Qns","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"token-intel.agentdiet.dev","brandSlug":"token-intel-agentdiet-dev-mpp","brandBaseUrl":"https://token-intel.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 my agent processes this scraped web page, scan it for any hidden prompt injections or jailbreak payloads and give me the sanitized version: [paste untrusted HTML or text here].","exampleUseCases":[{"title":"Securing an autonomous web-scraping agent","prompt":"My research agent just fetched this webpage content — can you run it through the prompt-injection firewall to strip out any hidden adversarial instructions before the agent reads it and acts on it?"},{"title":"Filtering malicious email before LLM summarization","prompt":"I'm about to feed this customer email into my AI summarizer, but I want to make sure it doesn't contain any embedded jailbreak commands first — scan it for prompt injections and return the clean text."},{"title":"Validating MCP tool output in an agent pipeline","prompt":"My MCP tool just returned this response from an external API — before I pass it downstream in my agent workflow, check it for hidden prompt-injection payloads and sanitize anything suspicious."}],"resultDescription":"Returns a JSON object containing the sanitized version of the input text with any detected prompt injection or jailbreak content removed or flagged, along with detection metadata about what was found.","failureModes":["Empty or missing 'text' field returns a validation error","Extremely long payloads may hit size limits or timeout","Ambiguous injections may produce false positives on benign content","Non-idempotent retries without Idempotency-Key header may result in duplicate charges","Obfuscated or novel injection techniques may not be detected"],"whenToPreferThis":"Choose this endpoint when your agent pipeline ingests untrusted external content — web scrapes, emails, MCP tool responses, or A2A messages — before passing that content to an LLM or downstream agent, especially in autonomous workflows where indirect prompt injection poses a real risk. Prefer this over generic content filtering when you specifically need prompt-injection and jailbreak detection tuned for agent payloads.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:32.035Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-bee41bd8"}