{"uid":"cap_1KRKd1dWemKOjORkbq1bq","slug":"trustsource-safefetch-a7ed473a","name":"TrustSource SafeFetch","description":"Fetch a URL safely and get back sanitized, agent-ready page text plus a prompt-injection verdict (SAFE / REVIEW / BLOCK). Detects instructions hidden in markup, invisible Unicode, homoglyph and encoded payloads, delimiter spoofing and data-exfiltration bait — so an agent never ingests hostile content. Use before feeding any fetched page into an LLM.","url":"https://api.trustsource.cc/safefetch","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":"Full URL to fetch and scan (e.g. https://example.com/article)."}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_CHTbOjk3HvVBCgRZwiA5G","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a URL safely, returning sanitized page text and a prompt-injection verdict (SAFE/REVIEW/BLOCK) by detecting hidden instructions, invisible Unicode, homoglyphs, encoded payloads, and data-exfiltration bait.","exampleAgentPrompt":"Before you feed the contents of https://example.com/article into your context, use SafeFetch to retrieve and scan it — I need to know whether it's SAFE, REVIEW, or BLOCK, and I want the sanitized text if it passes.","exampleUseCases":[{"title":"Agent reading user-submitted URLs","prompt":"A user just pasted https://some-blog.com/post into my chatbot and asked me to summarize it. Before I fetch and summarize it, can you run it through SafeFetch to make sure the page doesn't contain any prompt-injection tricks or hidden instructions?"},{"title":"Research agent pre-flight check","prompt":"I'm building a research agent that browses URLs from search results. Can you SafeFetch https://news-site.com/breaking-story and give me the sanitized page text plus the SAFE/REVIEW/BLOCK verdict before I pass it to my summarizer?"},{"title":"Content pipeline security gate","prompt":"We're scraping product pages for an e-commerce comparison tool. Before processing https://competitor-shop.com/product/widget, scan it with SafeFetch so we know if there are any embedded prompt injections or data-exfiltration baits hiding in the markup."}],"resultDescription":"Returns sanitized, agent-ready plain text extracted from the fetched page, along with a prompt-injection verdict of SAFE, REVIEW, or BLOCK. The verdict reflects detection of hidden markup instructions, invisible Unicode characters, homoglyph substitutions, encoded payloads, delimiter spoofing, and data-exfiltration bait. Agents can use the text only if the verdict is SAFE or acceptable under their policy.","failureModes":["URL is unreachable or returns a non-200 HTTP status — endpoint may return an error or empty content","Target page blocks crawlers (robots.txt disallowed) — content may not be retrievable","Page is behind authentication or a paywall — sanitized text will be incomplete or empty","Very large pages may be truncated or time out","Dynamic JavaScript-rendered content may not be fully captured if the page requires JS execution","Missing or malformed 'url' query parameter causes a validation error"],"whenToPreferThis":"Use this endpoint whenever an AI agent needs to fetch and process content from an external URL before passing it to an LLM — especially when the URL is user-supplied, untrusted, or from an unknown source. It is the right choice over a plain HTTP fetch when prompt-injection safety matters, since it combines content retrieval, sanitization, and threat classification in one call. Prefer it over generic web-scraping APIs when you need the SAFE/REVIEW/BLOCK verdict alongside clean text, rather than raw HTML or structured data extraction.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T00:31:20.487Z","isFirstParty":false}