{"uid":"cap_r_BvfyYEZIObWS-UFvULn","slug":"verdict-canary-check-53340ac0","name":"Verdict Canary Check","description":"Did a model reply leak what it should keep secret? Canary tokens and secret phrases searched by code (even split, spaced or uppercased), then paraphrases of the system prompt read by the engine. Returns clean, review or leak.","url":"https://verdict.kechlab.com/v1/canary-check?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"output":{"type":"string","description":"the model reply to check"},"canaries":{"type":"array","items":{"type":"string"},"description":"list of 1 to 10 tokens or phrases that must never come out"},"secret_text":{"description":"(optional) confidential text (system prompt) whose paraphrases are also searched"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.0092","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":"$0.0092/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0092","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0092","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_VHDeHSN_mTXKaNF84qHtY","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.0092","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Detects if a model reply has leaked secret canary tokens or paraphrased a confidential system prompt, returning clean, review, or leak.","exampleAgentPrompt":"Check this model reply for leaks — my canary tokens are ['CANARY-7X', 'secret-phrase-alpha'] and here's the full model output: 'Sure! Here is the answer...' — also compare against my system prompt so any paraphrases get flagged too.","exampleUseCases":[{"title":"System prompt theft detection","prompt":"I'm worried someone used prompt injection to extract my system prompt. Here's the model output I got back — my canary token is 'VAULT-42-TOKEN' and my system prompt text is attached. Tell me if any of it leaked, even if it's paraphrased or uppercased."},{"title":"Chatbot canary monitoring","prompt":"After every user conversation, check the chatbot's reply to make sure none of these secret phrases appeared: ['do-not-repeat-this', 'confidential-key-99']. Here's the latest reply — flag it as clean, review, or leak."},{"title":"Red-team LLM audit","prompt":"I'm red-teaming an LLM and need to know if my test output contains any of my planted canary tokens — 'REDTEAM-CANARY-A', 'REDTEAM-CANARY-B'. Scan this reply and tell me the verdict, including if the words are split, spaced, or uppercased."}],"resultDescription":"Returns a verdict of 'clean', 'review', or 'leak' indicating whether the model reply contained canary tokens (even obfuscated via splitting, spacing, or case changes) or paraphrases of the supplied confidential system prompt text.","failureModes":["More than 10 canary tokens supplied — input validation error","Empty or missing 'output' field — required field error","Ambiguous paraphrase detection may produce 'review' for borderline cases requiring human inspection","Very long model replies may increase processing time","False positives on common words that coincidentally match partial canary patterns"],"whenToPreferThis":"Use this endpoint when you need to detect confidential data leakage from LLM outputs — specifically when you have planted canary tokens or a private system prompt and want to verify the model reply hasn't exposed them, even in obfuscated form. Prefer this over generic PII detectors (another sibling endpoint) when your concern is canary token leakage or system prompt extraction rather than personal data. Ideal for security-conscious agentic pipelines, red-teaming workflows, or production chatbots where system prompt confidentiality is critical.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:18:59.488Z","isFirstParty":false,"canonicalSlug":"verdict-canary-check-53340ac0"}