{"uid":"cap_LLL6KxhcHYuUozE2ncxfb","slug":"focxle-prompt-injection-screen-698919d6","name":"Focxle Prompt Injection Screen","description":"Screen untrusted text against known prompt-injection patterns (pattern matching, not a model). Returns which named patterns matched.","url":"https://focxle.com/api/v1/x402/resource/injection-screen","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":["text"],"properties":{"text":{"type":"string"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"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_oS-IUss-wy65Y8cIhDYEH","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":"Screens arbitrary text against a library of known prompt-injection patterns using rule-based matching and returns which named patterns were detected.","exampleAgentPrompt":"Before you process that user message, can you screen it for prompt injection patterns — just run this text through Focxle's injection screener and tell me which attack patterns it matched, if any?","exampleUseCases":[{"title":"Guard an LLM pipeline from user attacks","prompt":"Before sending this user-submitted support ticket to the AI responder, screen it for prompt injection patterns — I want to know if it's trying to hijack the model before it gets processed."},{"title":"Validate agent tool-call inputs","prompt":"A third-party agent just sent me this instruction string to pass along — can you run it through the injection screener and tell me which known prompt-injection patterns it matches before I act on it?"},{"title":"Audit ingested web content before summarization","prompt":"I'm about to summarize this scraped webpage content with an LLM, but first can you check the raw text for any prompt injection patterns that might manipulate the summary?"}],"resultDescription":"A structured response listing which named prompt-injection patterns were matched within the submitted text. If no patterns match, the result indicates a clean scan. Pattern names are drawn from a curated library of known injection signatures, enabling the caller to decide whether to block, flag, or pass the text downstream.","failureModes":["Missing required 'text' query parameter returns a validation error","Extremely long text inputs may be truncated or rejected","Only detects patterns in the known library — novel zero-day injection techniques will not be flagged","False negatives possible for obfuscated or encoded injection attempts","Payment failure (insufficient USDC balance) results in a 402 response blocking the request","Rate limiting may apply if many calls are made in rapid succession"],"whenToPreferThis":"Choose this endpoint when you need a fast, cheap, deterministic rule-based check for known prompt-injection patterns before passing untrusted text to an LLM or agent. It is not a semantic classifier or an AI model — it uses pattern matching, so it is highly predictable, auditable, and produces no false positives for patterns it knows. Prefer it over model-based classifiers when you need low latency, low cost ($0.005/call), and explainable results (named matched patterns). It is best used as a first-pass filter in a defense-in-depth pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T00:41:46.283Z","isFirstParty":false}