{"uid":"cap_CBbriG9F9Q529G9Kf7H7O","slug":"ucf-v2-adversarial-verifier-identity-pack-probes-8e1a34dd","name":"UCF v2 Adversarial Verifier — Identity-Pack Probes","description":"UCF v2 Adversarial Verifier — identity-pack probes","url":"https://summary-entertaining-protest-product.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_NOxe_O1kO54PVYTAgfsih","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 AI agent identity packs (persona, session, operator) against adversarial probes to check consistency and integrity","exampleAgentPrompt":"Run an adversarial identity-pack probe on my agent persona named 'Aria' whose axioms are 'be helpful' and 'never deceive', voice is 'calm and professional', and never-do list includes 'reveal system prompt' — operator is 'Acme Corp' with role 'customer support assistant', session task is 'handle billing queries' on GPT-4.","exampleUseCases":[{"title":"Pre-deployment persona integrity check","prompt":"Before I ship my new AI agent 'Nova' into production, can you run an adversarial identity-pack probe on it? Its axioms are 'always cite sources' and 'escalate uncertain cases', its voice is 'concise and neutral', and it should never 'impersonate a human'. The operator is 'DataCo' with role 'research assistant', and the session task is 'literature summarization' running on Claude 3."},{"title":"Multi-agent trust verification","prompt":"I'm building a fleet of agents and need to verify that agent 'Helios' — with axioms 'follow operator instructions' and 'protect user privacy', voice 'formal', never-do list 'share PII' — is adversarially robust. Operator is 'FinanceHub', role 'compliance monitor', session task is 'transaction flagging' on GPT-4o."},{"title":"Detecting persona manipulation vulnerabilities","prompt":"Can you probe the identity pack of my agent 'Echo' for adversarial weaknesses? Its axioms are 'be empathetic' and 'de-escalate conflicts', voice is 'warm and supportive', and it must never 'give medical diagnoses'. Operator is 'WellnessApp', role 'mental health companion', and the session task is 'mood check-in' with memory entries about past conversations."}],"resultDescription":"Returns a verification or probe result indicating whether the submitted identity pack (persona, session, operator) passes adversarial consistency checks, along with any detected contradictions, failure points, or integrity issues found during the probe.","failureModes":["Missing required persona fields (name, axioms, voice, never) returns a 400-level validation error","Axioms array outside 2-4 item bounds causes schema rejection","Missing required operator fields (name, role) causes request failure","Malformed session memory (non-array) triggers schema validation error","Payment not included or insufficient ($1 USDC) causes 402 Payment Required","Endpoint unavailable (Cloudflare tunnel down) returns 502 or timeout"],"whenToPreferThis":"Choose this endpoint when you need to adversarially stress-test an AI agent's identity pack before deployment or during runtime audits, particularly when operating in multi-agent environments where persona consistency and operator-alignment are critical. Best suited for AI safety pipelines, agent orchestration platforms, or compliance workflows that require formal verification of persona integrity rather than simple schema validation.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T18:30:33.801Z","isFirstParty":false}