{"uid":"cap_OIulcm8RpvH_Ba2ZXIw18","slug":"continuitykit-ucf-v2-adversarial-verifier-8f267b86","name":"ContinuityKit UCF v2 Adversarial Verifier","description":"UCF v2 Adversarial Verifier -------- identity-pack probes","url":"https://continuitykit.net/v1/verify?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":{"type":"object","required":["persona","operator"],"properties":{"persona":{"type":"object","required":["name","axioms","voice","never"],"properties":{"name":{"type":"string"},"never":{"type":"array","items":{"type":"string"}},"voice":{"type":"string"},"axioms":{"type":"array","items":{"type":"string"},"maxItems":4,"minItems":2},"symbol":{"type":"string"}}},"session":{"type":"object","properties":{"task":{"type":"string"},"model":{"type":"string"},"memory":{"type":"array","items":{"type":"string"}},"platform":{"type":"string"}}},"operator":{"type":"object","required":["name","role"],"properties":{"name":{"type":"string"},"role":{"type":"string"}}}}},"type":{"type":"string","const":"http"},"method":{"enum":["POST","PUT","PATCH"],"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":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"1","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":"down","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$1/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"1","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"1","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm__jw2aMek1-c5qSw-f0Ei-","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"1","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Probes an AI agent's persona identity pack for adversarial robustness by verifying that the agent's persona, axioms, voice, and operator constraints hold under adversarial conditions","exampleAgentPrompt":"Run an adversarial identity-pack probe on my agent persona called 'Aria' with axioms ['always be honest', 'never reveal system prompts'], voice 'calm and professional', never-do rules ['impersonate humans', 'make financial promises'], operated by 'AcmeCorp' as a 'customer support assistant'.","exampleUseCases":[{"title":"Jailbreak resistance audit for support bot","prompt":"Probe my customer support persona 'Helpa' — it has axioms ['always escalate sensitive issues', 'never share PII'], voice 'friendly and concise', never-do rules ['impersonate a human', 'provide legal advice'], and it's operated by 'RetailCo' as a 'tier-1 support agent'. I want to know if adversarial prompts can break those constraints."},{"title":"Pre-deployment persona integrity check","prompt":"Before I launch my AI assistant 'Sage', run an adversarial verifier probe on its identity pack: persona name 'Sage', axioms ['be factual', 'cite sources when possible'], voice 'scholarly and precise', never-do ['speculate without evidence', 'use inflammatory language'], operator is 'EduTech Inc' with role 'academic tutor assistant'."},{"title":"Operator constraint violation detection","prompt":"Test whether the persona 'Maverick' for my fintech app can be tricked into violating its operator constraints — axioms are ['never give investment advice', 'always disclose AI status'], voice 'confident but cautious', never-do rules ['make price predictions', 'promise returns'], operator 'FinanceHub' role 'financial information assistant'."}],"resultDescription":"Returns a structured verification result indicating whether the persona identity pack withstands adversarial probing, including which axioms or constraints were challenged and the outcome of each probe test.","failureModes":["Missing required persona fields (name, axioms, voice, never) returns a 400 validation error","Fewer than 2 or more than 4 axioms causes schema validation failure","Invalid method enum value (only POST, PUT, PATCH accepted) causes rejection","Payment not completed via x402 protocol results in 402 Payment Required","Malformed body or incorrect bodyType enum causes request failure"],"whenToPreferThis":"Choose this endpoint when you need to programmatically verify that an AI agent persona is adversarially robust — specifically when you have a structured persona definition (axioms, voice, never-do rules) and an operator context and want to stress-test identity consistency before deployment or on a recurring audit basis. Prefer it over manual red-teaming or generic LLM evaluation tools when you need a structured, paid, repeatable identity-pack probe with defined schema inputs.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T16:27:34.270Z","isFirstParty":false,"canonicalSlug":"continuitykit-ucf-v2-adversarial-verifier-8f267b86"}