{"uid":"cap_8Xwvq5VBwc_wST8S-2wDz","slug":"ucf-v2-adversarial-verifier-identity-pack-probes-0b768c15","name":"UCF v2 Adversarial Verifier – Identity-Pack Probes","description":"UCF v2 Adversarial Verifier — identity-pack probes","url":"https://unlike-tale-plays-rose.trycloudflare.com/v1/verify","method":"POST","headers":{},"bodySchema":{"type":"object","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"}}}}},"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":"unknown","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_CIMvudbDdIYUv8XmBeQkX","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":"Runs adversarial probe checks against a structured AI persona/identity pack to verify robustness, consistency, and boundary integrity.","exampleAgentPrompt":"Run an adversarial probe on my persona pack — the persona is named 'Aria', her axioms are 'always be honest' and 'never manipulate users', her voice is 'calm and empathetic', she must never insult users or break character, and the operator is 'Acme Corp' acting as 'customer support lead'. Check if she holds up.","exampleUseCases":[{"title":"Pre-deployment persona robustness audit","prompt":"Before we ship our support agent 'Nova', I need to verify her identity pack holds up under adversarial probing. Her axioms are 'stay on-topic' and 'never reveal internal pricing', her voice is 'professional and concise', she must never curse or claim to be human, and our operator is 'RetailCo' in the role of 'e-commerce assistant'. Run the identity probes and tell me if anything breaks."},{"title":"Jailbreak resistance check for a roleplay agent","prompt":"I've built a creative writing persona called 'Muse' with axioms 'encourage creativity' and 'avoid harmful content', a poetic voice, and hard limits on never producing violence or explicit content. The operator is 'StoryLabs' as 'creative director'. Can you adversarially probe Muse to see if those boundaries can be violated?"},{"title":"Operator compliance verification for regulated platform","prompt":"We're deploying a financial advisor persona named 'Sterling' on a regulated platform. His axioms are 'always recommend consulting a licensed advisor' and 'never give specific investment advice', his voice is 'measured and cautious', and he must never guarantee returns. The operator is 'FinEdge' as 'compliance officer'. Run adversarial identity checks and flag any probe that breaks compliance."}],"resultDescription":"Returns a structured adversarial verification report indicating whether the persona pack passed or failed identity probes, with details on which axioms, voice constraints, or never-do rules were challenged and whether they held, along with any boundary violations or consistency failures detected.","failureModes":["Missing required persona fields (name, axioms, voice, never) returns a 400-level validation error","Axioms array outside min/max bounds (fewer than 2 or more than 4) causes schema rejection","Missing required operator fields (name, role) returns a validation error","Payment not included or insufficient USDC causes a 402 Payment Required response","Transient Cloudflare tunnel errors may cause 503 or connection timeouts","Malformed session memory array causes unpredictable probe behavior"],"whenToPreferThis":"Choose this endpoint when you need to adversarially stress-test a UCF v2 persona/identity pack before deployment, specifically running identity probes to check if the persona resists manipulation, stays in-voice, and honors its never-do constraints. Prefer this over generic LLM safety checkers when working within the UCF (Unified Character Framework) v2 ecosystem and needing structured probe results tied to persona axioms, voice, and operator context.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-16T00:37:23.524Z","isFirstParty":false}