{"uid":"cap_eWSlNLASvFq44a-MhTdKi","slug":"prompt-injection-scanner-bc7c61f7","name":"Prompt Injection Scanner","description":"Scan text an agent is about to read (web page, email, tool result; up to 8,000 characters) for prompt-injection attempts: instruction overrides, fake system messages, asks to hide things from the user, exfiltration links, attempts to extract private data or move money, invisible Unicode. Returns a risk level, score and findings with excerpts. Heuristic, not a guarantee. Use before acting on untrusted content.","url":"https://agent-data-tools.revmesh2074.workers.dev/text/prompt-injection?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","required":["text"],"properties":{"text":{"type":"string","description":"The text to scan (up to 8,000 characters)"}}},"responseSchema":{"type":"object","properties":{"risk":{"type":"string"},"score":{"type":"number"},"findings":{"type":"array","items":{}},"hiddenCharacters":{"type":"object","properties":{"bidi":{"type":"number"},"tags":{"type":"number"},"zeroWidth":{"type":"number"}}}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USD","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_ju8XcmKRCdmKTDUtZkwxQ","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":"Scans up to 8,000 characters of text for prompt-injection attacks, instruction overrides, hidden Unicode, and data-exfiltration attempts, returning a risk level, score, and excerpted findings.","exampleAgentPrompt":"Before you process that webpage you just fetched, scan the full text for prompt injection — instruction overrides, fake system messages, exfiltration links, or hidden Unicode — and tell me the risk level and what you found.","exampleUseCases":[{"title":"Guard agent before acting on web scrape","prompt":"I'm about to have my agent summarize this scraped article, but first scan its full text for any prompt injection attempts, hidden Unicode, or instructions trying to hijack the agent — give me the risk score and any excerpts that look suspicious."},{"title":"Screen incoming email before agent reads it","prompt":"My agent is going to process this customer email and draft a reply — can you first check the email body for prompt injection, fake system instructions, or attempts to extract private data, and tell me if it's safe to proceed?"},{"title":"Validate tool result before pipeline continues","prompt":"My automation just got back a result from an external tool — scan it for prompt injection before the next step uses it, especially check for instruction overrides and any invisible bidirectional or zero-width characters."}],"resultDescription":"Returns a JSON object with: a `risk` string (e.g. 'low', 'medium', 'high'), a numeric `score`, a `findings` array containing excerpts and descriptions of detected threats, and a `hiddenCharacters` object counting bidirectional override characters, Unicode tag characters, and zero-width characters found in the input.","failureModes":["Text exceeding 8,000 characters may be truncated or rejected","Heuristic detection — sophisticated injections may evade the scanner","False positives on legitimate content that resembles injection patterns","Missing or empty `text` parameter returns a validation error","Payment/authentication failure returns 402 Payment Required"],"whenToPreferThis":"Use this endpoint as a security gate before your AI agent acts on any untrusted external content — web pages, emails, API responses, PDFs, or user-supplied text. It is especially valuable in agentic pipelines where acting on injected instructions could cause financial transactions, data exfiltration, or unauthorized actions. Prefer this over general-purpose text analysis when your specific concern is adversarial prompt manipulation targeting the AI agent itself.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-30T07:12:49.490Z","isFirstParty":false,"canonicalSlug":"prompt-injection-scanner-bc7c61f7"}