{"uid":"cap_WjWI0GakzkGCZ1UXIajqy","slug":"agent-tools-safe-web-read-with-prompt-injection-detection-f1d134f4","name":"Agent Tools – Safe Web Read with Prompt Injection Detection","description":"Pay-per-call utilities for AI agents over x402, USDC on Base.","url":"https://agents.crowdspark.me/v1/web/safe-read?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"Public page URL"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"url":"https://example.com/","title":"Example Domain","status":200,"markdown":"This domain is for use in documentation examples...","injection":{"score":0,"matches":[],"verdict":"safe","categories":{}},"characters":156}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.005","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":"$0.005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_S2KO1prVKFMa5s-7ISB5t","protocol":"x402","methodType":"crypto","chain":"base","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":"Fetches a public web page, converts it to clean markdown, and screens it for prompt injection attacks, returning a safety verdict, score, and matched spans.","exampleAgentPrompt":"Before you summarize that article, safely fetch https://example.com/article and check whether it contains any prompt injection — give me the clean markdown and tell me if it's safe, suspicious, or malicious.","exampleUseCases":[{"title":"Safe summarization of unknown URLs","prompt":"I need you to fetch https://techblog.example.com/new-post and check it for prompt injection before summarizing it — show me the verdict and score, and only summarize it if it comes back safe."},{"title":"Screening user-submitted links before agent ingestion","prompt":"A user just submitted this link for our agent to process: https://user-submitted.example.com/data — can you safe-read it and tell me if there's any injection attempt before we feed it into context?"},{"title":"Research assistant reading competitor pages safely","prompt":"Pull the content from https://competitor.example.com/pricing as clean markdown and scan it for any adversarial content targeting AI agents — I want to know the injection score and any matched spans before we use it."}],"resultDescription":"Returns JSON with: the page URL, title, HTTP status code, full page content as clean markdown, character count, and an injection object containing a 0–100 numeric score, a verdict string ('safe', 'suspicious', or 'malicious'), matched injection spans, and matched categories.","failureModes":["URL is blocked by robots.txt — endpoint respects robots.txt and may refuse to fetch","Target URL is unreachable or returns a non-200 status","Page content is non-textual (e.g. binary files, video) and cannot be converted to markdown","Payment not received or x402 payment flow fails, resulting in 402 response","Malformed or missing 'url' query parameter returns a validation error","Target server rate-limits or blocks the crawler IP"],"whenToPreferThis":"Choose this endpoint when your agent needs to read an untrusted or user-supplied URL and you want both clean markdown extraction and prompt injection screening in a single call, avoiding the need to chain a scraper with a separate safety filter. Especially valuable in agentic pipelines where adversarial web content could hijack the agent's behavior. Prefer over generic scrapers when agent safety is a concern.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-02T12:30:35.458Z","isFirstParty":false,"canonicalSlug":"agent-tools-safe-web-read-with-prompt-injection-detection-f1d134f4"}