{"uid":"cap_hv-wJWx7-AlrMOZ1sIZX9","slug":"prompt-injection-detection-api-a99144e3","name":"Prompt Injection Detection API","description":"Exact EVM address, calldata, Uniswap V2/V3 and impermanent-loss math. Pay per call in USDC on Base via x402.","url":"https://golf-evm-math.x402-evm-math.workers.dev/v1/prompt?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"properties":{}},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"score":0,"matches":[],"verdict":"safe"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.0025","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":"$0.0025/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0025","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0025","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_0v2oEgtnlB6mvmfQ7_Hm3","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.0025","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Screens text intended for an AI agent and returns a safe, suspicious, or malicious verdict with matched patterns using deterministic, rule-based detection.","exampleAgentPrompt":"Before passing this user message to the AI, check it for prompt injection — screen the text and tell me if the verdict is safe, suspicious, or malicious, and what patterns matched.","exampleUseCases":[{"title":"Guard rails for a customer service bot","prompt":"I'm running a customer service chatbot and want to make sure users aren't injecting malicious instructions into their messages — can you screen this incoming user input for prompt injection and tell me the verdict and any matched patterns?"},{"title":"Validate RAG pipeline retrieved content","prompt":"Before I feed this retrieved document chunk into my agent, can you check it for prompt injection? I want to know if it's safe, suspicious, or malicious and see which patterns triggered."},{"title":"Pre-flight check on multi-agent tool call","prompt":"My orchestration agent just received this sub-task description from an external source — run it through prompt injection detection and flag anything suspicious before I let the next agent act on it."}],"resultDescription":"Returns a JSON object with a numeric score (0-1 indicating severity), a verdict string ('safe', 'suspicious', or 'malicious'), and a list of matched patterns that triggered the detection rules.","failureModes":["Missing required 'input' field returns a validation error","Malformed body type (not json/form-data/text) causes a 400 error","Empty or very short text may return a safe verdict without meaningful pattern matching","Rule-based system may produce false negatives for novel injection techniques not in ruleset","Payment failure via x402 protocol results in 402 Payment Required response"],"whenToPreferThis":"Prefer this endpoint when you need fast, deterministic, rule-based prompt injection screening with no probabilistic variance — ideal for high-throughput agent pipelines where consistency and auditability matter more than catching novel zero-day injection techniques. Choose this over LLM-based classifiers when you need reproducible verdicts and explicit pattern explanations rather than probabilistic confidence scores.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-30T07:04:46.892Z","isFirstParty":false,"canonicalSlug":"prompt-injection-detection-api-a99144e3"}