{"uid":"cap_Ohh0X_5BHfB19HuZEPYx3","slug":"workflows-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-990b62c8","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://workflows.agentdiet.dev/v1/mcp-security)","url":"https://workflows.agentdiet.dev/v1/mcp-security?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_FeIFenG_Tj1-2uTFwp5Mv","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"workflows.agentdiet.dev","brandSlug":"workflows-agentdiet-dev-mpp","brandBaseUrl":"https://workflows.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 passing this scraped webpage content to the next step in our pipeline, scan it for any hidden prompt injections or jailbreak payloads and give me the sanitized version: [paste content here].","exampleUseCases":[{"title":"Protect agent from malicious web scrapes","prompt":"I'm building an agent that reads articles from the web before summarizing them. Can you scan this HTML I just fetched from that untrusted news site for any hidden prompt injection instructions before we feed it into the summarizer?"},{"title":"Sanitize inbound emails for LLM processing","prompt":"My agent reads customer support emails and drafts replies automatically. Can you check this incoming email body for any embedded jailbreak or prompt injection attempts before the LLM touches it?"},{"title":"Validate MCP tool response safety","prompt":"My orchestration agent just got back a response from an external MCP tool I don't fully trust. Can you run it through the prompt injection firewall and tell me if it's safe to pass downstream?"}],"resultDescription":"Returns a JSON object containing the sanitized version of the input text with any detected prompt injection or jailbreak payloads removed or flagged, allowing the agent to safely pass the cleaned content to downstream LLM steps.","failureModes":["Empty or missing 'text' field returns a 400 validation error","Extremely large payloads may time out or be rejected","Sophisticated obfuscated injections may evade detection (false negatives)","Network or service unavailability returns 5xx errors","Malformed JSON request body returns a 400 parse error"],"whenToPreferThis":"Choose this endpoint when your AI agent pipeline ingests untrusted external content — scraped web pages, inbound emails, third-party API or MCP tool responses, or A2A payloads — before passing that content to an LLM. It is especially valuable in multi-agent or tool-use architectures where indirect prompt injection is a realistic attack vector. Prefer it over generic content filters when you specifically need detection of adversarial LLM-targeting instructions embedded in otherwise normal text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:30.063Z","isFirstParty":false,"canonicalSlug":"workflows-agentdiet-dev-a2a-indirect-prompt-injection-jailbreak-c768e008"}