{"uid":"cap_Xbst-ZyVNEtGwHlLSCCif","slug":"sentinel-agent-safety-guard-dce8a8b5","name":"Sentinel Agent Safety Guard","description":"SENTINEL pre-execution safety verdict","url":"https://sentinel-agent.dev/v1/guard","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string"},"method":{"type":"string"}}},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"}}}}},"responseSchema":{"type":"json","example":{"risks":[],"verdict":"SAFE","signature":"base64..."}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.005","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":"$0.005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_PjfGFCuUuYSpZGcALeZAS","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Evaluates an agent action before execution and returns a pre-execution safety verdict to allow or block the action","exampleAgentPrompt":"Before I let the agent call the 'transfer_funds' method of type 'financial_transaction', run a Sentinel safety check on that action and tell me whether it's safe to proceed.","exampleUseCases":null,"resultDescription":"A pre-execution safety verdict indicating whether the specified agent action (identified by type and method) is allowed or should be blocked, along with any supporting safety assessment details.","failureModes":["Missing required 'input.type' or 'input.method' fields returns a 400 validation error","Malformed input object structure causes schema validation failure","Network timeout if the safety evaluation takes too long","Payment failure via x402 protocol results in 402 Payment Required before verdict is issued","Unknown or unsupported action types may return an inconclusive verdict"],"whenToPreferThis":"Use this endpoint when an AI agent needs a safety gate before executing potentially dangerous, irreversible, or sensitive actions — especially financial transactions, system modifications, or external communications. Prefer Sentinel over post-execution logging when the cost of a bad action is high and you need a block/allow decision before the action runs.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T06:33:16.805Z","isFirstParty":false}