{"uid":"cap_xghuNiodlShkxLTWu301A","slug":"agent402-uk-text-firewall-f1ff7724","name":"Agent402 UK Text Firewall","description":"Don't burn tokens on deterministic work. Go/no-go jobs first: payout preflight, text firewall (PII/secrets), budget check — then rails, calendars, finmath. x402 USDC on Base. UK + global. agent402.co.uk — not agent402.tools. $0.001–$0.002 USDC on Base. No API keys.","url":"https://agent402.co.uk/v1/jobs/text-firewall","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"mode":{"type":"string","description":"scan | redact"},"text":{"type":"string","description":"Log, prompt, or tool I/O (max 100k chars)"},"block":{"type":"array","description":"Kinds that force allow=false"},"include":{"type":"array","description":"secret and/or pii (default both)"},"replacement":{"type":"string","description":"Redaction token, default [REDACTED]"}}},"responseSchema":{"type":"json","example":{"allow":true,"valid":true,"redacted":"contact [REDACTED]:email — do not paste keys","finding_count":1}},"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_w5iP-8JO06h60Xjl4vUal","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":"Scans or redacts PII and secrets from text (logs, prompts, tool I/O) and returns a go/no-go allow flag with findings count","exampleAgentPrompt":"Before you send that tool output to the next step, run it through the Agent402 text firewall in redact mode to strip out any PII or secrets — use both pii and secret detection and replace anything found with [REDACTED].","exampleUseCases":[{"title":"Safe LLM prompt forwarding","prompt":"Scan this user message for any email addresses, phone numbers, or API keys before you include it in the next LLM prompt — if anything is found, redact it with [REDACTED] and tell me how many findings there were."},{"title":"Agent log sanitisation before storage","prompt":"I'm about to write this agent execution log to our database — run it through the text firewall in redact mode covering both PII and secrets, and only proceed if the allow flag comes back true."},{"title":"Go/no-go check on outbound webhook payload","prompt":"Check this webhook payload for any sensitive data before we post it to the third-party endpoint — scan mode, block on secrets, and give me the allow decision and finding count."}],"resultDescription":"A JSON object with: `allow` (boolean go/no-go), `valid` (boolean), `redacted` (text with sensitive spans replaced by the redaction token), and `finding_count` (integer number of detected items). In scan mode the original text is not altered; in redact mode the redacted field contains the cleaned text.","failureModes":["Text exceeds 100,000 character limit — request rejected","Invalid mode value (not 'scan' or 'redact') — validation error returned","Malformed JSON body — 400 error","Payment not received or USDC balance insufficient on x402 — 402 Payment Required","Network timeout on large payloads"],"whenToPreferThis":"Choose this endpoint when you need a fast, cheap, deterministic PII/secrets scan without spending LLM tokens on the task — ideal as a pre-flight check before logging, forwarding, or storing any agent-generated or user-supplied text. Prefer it over LLM-based redaction for cost and consistency; it costs $0.001 USDC per call, requires no API key, and returns a structured allow flag usable in conditional workflow logic.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:33:08.503Z","isFirstParty":false}