{"uid":"cap_XLN9rkv_4dTajE_vnkezV","slug":"ucf-v2-adversarial-verifier-identity-pack-probes-678324b4","name":"UCF v2 Adversarial Verifier – Identity-Pack Probes","description":"UCF v2 Adversarial Verifier — identity-pack probes","url":"https://food-odds-award-exhaust.trycloudflare.com/v1/verify","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_ImJgjNFPumfFG19Py8Az6","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":"Verifies an AI identity pack (persona + operator) against adversarial probes to test robustness and behavioral consistency","exampleAgentPrompt":"Run adversarial identity probes on my UCF persona called 'Aria' — her axioms are 'be helpful' and 'never deceive', her voice is 'calm and precise', she must never threaten users, and the operator is 'AcmeCorp' acting as a customer support provider.","exampleUseCases":[{"title":"Pre-deployment persona robustness audit","prompt":"Before I launch my AI assistant 'Nova', I want to run adversarial probes on her identity pack — her axioms are 'be empathetic' and 'prioritize user safety', her voice is 'warm and concise', she must never share personal data or use manipulative language, and the operator is 'HealthBot Inc' in a clinical support role."},{"title":"Testing operator-persona alignment under hostile inputs","prompt":"Can you verify that my persona 'Sentinel' with axioms 'protect user privacy' and 'defer to human oversight' holds up against adversarial probes? His voice is 'formal and measured', he must never impersonate authorities, and the operator is 'SecureOps' acting as a security monitoring agent."},{"title":"Validating a creative AI character's behavioral guardrails","prompt":"I need to stress-test my storytelling persona 'Muse' — axioms are 'inspire creativity' and 'stay age-appropriate', voice is 'playful and imaginative', never-do rules include no graphic violence and no hate speech, and the operator is 'StoryForge' as a children's content platform."}],"resultDescription":"Returns a structured verification result object indicating whether the identity pack (persona + operator) passed adversarial probes, including probe outcomes and consistency assessments for the persona's axioms, voice, and behavioral constraints under adversarial conditions.","failureModes":["Missing required persona fields (name, axioms, voice, never) returns validation error","Axioms array outside 2–4 item bounds triggers schema rejection","Invalid HTTP method (only POST/PUT/PATCH accepted) returns method error","Malformed or non-JSON body returns parse error","Insufficient USDC balance or x402 payment failure blocks execution","Cloudflare tunnel downtime causes connection errors","Operator object missing name or role returns required-field error"],"whenToPreferThis":"Choose this endpoint when you need to adversarially probe and validate an AI persona identity pack before deployment, specifically within the UCF v2 framework. It is the right choice when you want to ensure persona axioms, voice, and behavioral constraints hold up under hostile or edge-case inputs. Prefer this over generic prompt-testing tools when you have a structured UCF-format identity pack and need structured, schema-grounded adversarial verification rather than informal manual testing.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T16:27:22.302Z","isFirstParty":false}