{"uid":"cap_TI0jxRnNyYk3-ZQrujFfM","slug":"email-guard-e66aa547","name":"Email Guard","description":"Read one email the way an agent that triages mail should before acting on it: observations with evidence and offsets, no score and no verdict. Send the raw RFC 5322 message (multipart, base64 and quoted-printable decoded, 1 MB cap) or the parts you already hold (subject, from, replyTo, html, text, links).","url":"https://agent402.tools/api/email-guard?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"raw":{"type":"string","description":"The whole RFC 5322 message as received, headers and body, multipart allowed (max 1 MB). Send this or the parts below, not both."},"from":{"type":"string","description":"From header, display name and address (parts mode)"},"html":{"type":"string","description":"The text/html part (parts mode, max 1 MB)"},"text":{"type":"string","description":"The text/plain part (parts mode, max 1 MB)"},"links":{"type":"array","items":{"oneOf":[{"type":"string"},{"type":"object","required":["href"],"properties":{"href":{"type":"string"},"text":{"type":"string"}}}]},"description":"Links already extracted from the mail, as hrefs or { href, text } (parts mode, max 500)"},"replyTo":{"type":"string","description":"Reply-To header (parts mode)"},"subject":{"type":"string","description":"Subject header (parts mode)"}}},"responseSchema":{"type":"json","example":{"note":"full example in /openapi.json","truncated":true}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001","displayCostAsset":"USDC","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":"$0.001/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_RNQRh4nGIYvS9L2AyBhjS","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Analyzes a raw email or its parsed parts and returns structured observations with evidence and text offsets to help agents triage mail — no score, no verdict, just findings.","exampleAgentPrompt":"I just received this raw email and need you to analyze it before I act on it — here's the full RFC 5322 message including headers and body. Give me structured observations with evidence and the exact offsets where you found them, but no spam score or verdict.","exampleUseCases":[{"title":"Phishing link detection in inbox","prompt":"I have an email from 'support@paypal-secure.net' with this subject 'Your account has been limited' and these links extracted from it — can you analyze the email parts and tell me what observations stand out, with the exact evidence from the text?"},{"title":"Support inbox triage agent","prompt":"Before my agent auto-replies to this customer email, analyze the raw message I'm passing and return any observations about mismatched headers, suspicious links, or unusual content patterns so I can decide whether to flag it for human review."},{"title":"Security audit of forwarded email","prompt":"Someone forwarded me this suspicious email as a raw .eml file — here's the full RFC 5322 content including all headers. Can you read it and give me structured observations with evidence and character offsets pointing to anything that looks off?"}],"resultDescription":"A JSON object containing a list of structured observations about the email, each with supporting evidence (quoted excerpts) and character offsets locating the finding within the message. No aggregate score or final verdict is returned — findings are raw and factual for the agent to reason over.","failureModes":["Payload exceeds 1 MB cap — request rejected","Both 'raw' and parts fields submitted simultaneously — conflict error","Malformed RFC 5322 message that cannot be parsed — parse error returned","Empty or missing required fields in parts mode — validation error","Base64 or quoted-printable decoding failure on malformed encodings"],"whenToPreferThis":"Choose this endpoint when you need structured, evidence-backed observations about an email without a black-box verdict — ideal for agentic workflows where the agent itself decides what to do with the findings. Prefer it over spam filters when you need explainability, text offsets, and raw evidence rather than a simple pass/fail score. Well-suited for triage pipelines that must handle raw RFC 5322 messages including multipart and encoded payloads.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-30T00:35:35.121Z","isFirstParty":false,"canonicalSlug":"email-guard-e66aa547"}