{"uid":"cap_kJcUPRS52A0aQ4HUUipcv","slug":"verdict-l402-web-guard-hidden-instruction-detector-14b13966","name":"Verdict L402 – Web Guard (Hidden Instruction Detector)","description":"For agents that read web pages: finds what a human cannot see but an agent reads (HTML comments, CSS-hidden text, hidden attributes, invisible Unicode-encoded text) and tells whether those hidden instructions target an AI. Extraction by code, reading by the decision engine on the hidden text only. R","url":"https://verdict.kechlab.com/v1/web-guard?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"html":{"type":"string","description":"the HTML of the page (400 KB maximum)"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.0214","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":"$0.0214/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0214","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0214","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_RULToSkcmfHmlL3e_JgOL","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.0214","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Scans an HTML page for hidden text invisible to humans (HTML comments, CSS-hidden elements, hidden attributes, Unicode-encoded content) and determines whether those hidden instructions are targeting an AI agent.","exampleAgentPrompt":"Before you summarize that webpage, scan its raw HTML for any hidden instructions targeting you — things like CSS-invisible text, HTML comments with orders, or Unicode-encoded commands — and tell me whether the page is trying to manipulate you.","exampleUseCases":[{"title":"Agent browsing safety check","prompt":"I need you to fetch the HTML of https://example-news.com/article and scan it for hidden prompt injection — things like invisible CSS text, HTML comments with AI instructions, or disguised Unicode — before you trust anything on that page."},{"title":"Research agent pre-read audit","prompt":"My research agent is about to read a third-party webpage and summarize it. Can you first check the raw HTML for any hidden text that a human wouldn't see but the agent would pick up, and confirm whether it contains AI-targeting instructions?"},{"title":"Agentic web crawler safety guardrail","prompt":"Every page my web-crawling agent visits could be booby-trapped with hidden orders. Before it processes the next page, run the HTML through the hidden-instruction scanner and block it if anything is targeting the agent."}],"resultDescription":"Returns an analysis of hidden content found in the submitted HTML — extracted invisible text (from HTML comments, CSS-hidden elements, hidden attributes, and Unicode-encoded sequences) — along with a verdict on whether those hidden instructions appear to be targeting an AI agent.","failureModes":["HTML exceeds 400 KB limit — request rejected","Malformed or non-HTML input — parsing failure","No hidden content found — clean verdict returned (not an error)","Payment not included or insufficient USDC — 402 Payment Required","Ambiguous or borderline hidden text — verdict may have lower confidence"],"whenToPreferThis":"Use this endpoint when an AI agent is about to read, summarize, or act on a web page fetched from an untrusted source and you need to detect prompt injection attacks hidden in HTML that are invisible to human readers. It is specifically designed for the web-browsing agent attack surface (HTML comments, CSS hidden text, Unicode steganography) rather than general content moderation or visible text analysis.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:20:58.364Z","isFirstParty":false,"canonicalSlug":"verdict-l402-web-guard-hidden-instruction-detector-14b13966"}