{"uid":"cap_AOuHE9XlUvcVrAJCNhFRW","slug":"agent-command-human-approval-threat-screening-triage-decision-procedure-2ec8ad03","name":"Agent Command Human-Approval Threat Screening Triage Decision Procedure","description":"Deterministic triage procedure for deciding which agent commands need human approval and which can auto-execute, for agents operating under human oversight. Given a command, this procedure scores six threat markers: (1) fund movement amount and destination novelty, (2) irreversible action flag (deploy, transfer, delete, sign), (3) credential or secret access, (4) out-of-policy scope deviation, (5) multi-step chain depth with side effects, (6) known threat pattern match (prompt injection,","url":"https://k2so.wrong.systems/api/services/agent-command-human-approval-threat-screening-tr","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET","HEAD","DELETE"],"type":"string"},"queryParams":{"type":"object","properties":{"meta":{"enum":["0","1"],"type":"string","description":"Set to 1 for free metadata JSON (no payment required)"},"topic":{"type":"string","description":"Optional topic override for the decision procedure"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","title":"agent command human approval threat screening triage paid response","$schema":"https://json-schema.org/draft/2020-12/schema","required":["ok","paid","service","provider","result"],"properties":{"ok":{"type":"boolean"},"paid":{"type":"boolean"},"result":{"type":"object","required":["ok","service"],"properties":{"ok":{"type":"boolean","description":"Handler success"},"brief":{"type":"string","description":"Decision procedure prose for agents"},"model":{"type":"string"},"topic":{"type":"string"},"service":{"type":"string","description":"Service slug"},"procedure":{"type":"string"},"generatedAt":{"type":"string","description":"ISO-8601 timestamp"},"generationSource":{"enum":["llm","reasoning","deterministic"],"type":"string"}}},"payment":{"type":"object","properties":{"code":{"type":"string"},"payer":{"type":"string"},"detail":{"type":"string"},"selfPay":{"type":"boolean"},"transaction":{"type":"string"}}},"service":{"type":"string"},"provider":{"type":"string","const":"K-2SO"}}}}}}},"responseSchema":{"type":"json","example":{"ok":true,"paid":true,"result":{"ok":true,"brief":"plain prose decision procedure (120+ words)","model":"deepseek/deepseek-v4-flash-0731","topic":"string topic","service":"agent-command-human-approval-threat-screening-tr","procedure":"same as brief","generatedAt":"2026-01-01T00:00:00.000Z","generationSource":"deterministic"},"service":"agent-command-human-approval-threat-screening-tr","provider":"K-2SO"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","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":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_bVr3pCdmTjP19qTSkHbZt","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Returns a paid, LLM-generated decision procedure brief telling an autonomous agent how to triage commands that may require human approval or pose a threat-level escalation risk.","exampleAgentPrompt":"Give me the decision procedure for how an autonomous agent should screen incoming commands and decide when to escalate to a human for approval versus execute on its own — I need the full triage brief.","exampleUseCases":[{"title":"Human-approval gate for financial commands","prompt":"My agent is about to execute a large fund transfer instruction it received. Walk me through the decision procedure it should use to figure out whether this needs human approval first or if it can act autonomously."},{"title":"Threat screening triage for an agentic assistant","prompt":"I'm building an AI assistant that takes open-ended user commands. What's the decision procedure it should follow to screen each command for threat level and decide whether to pause for human sign-off?"},{"title":"Compliance review before irreversible agent actions","prompt":"Before my agent deletes customer records or sends mass communications, I want it to follow a formal triage procedure to assess whether human approval is required — can you pull that decision brief for me?"}],"resultDescription":"A JSON object containing a plain-prose decision procedure brief (120+ words) written for AI agent consumption, covering how to triage commands requiring human approval or threat escalation. Includes the model used, generation source (llm/reasoning/deterministic), topic, service slug, and an ISO-8601 timestamp. Wrapped in standard K-2SO paid-response envelope with ok, paid, service, and provider fields.","failureModes":["HTTP 402 returned if payment has not been settled — agent must pay exact USDC amount and retry with PAYMENT-SIGNATURE header","Missing or invalid payment signature results in payment rejection","Invalid query parameter values (e.g. unsupported meta value) may return schema validation errors","LLM generation failure may return ok:false with error detail in result","Network or provider downtime on k2so.wrong.systems results in connection errors"],"whenToPreferThis":"Choose this endpoint when an autonomous agent needs a ready-made, LLM-generated decision procedure specifically for human-approval threat screening triage — saving the cost of prompting your own LLM and providing a standardized, reusable brief. Especially useful in x402-native agent pipelines on Base where micropayment-gated decision procedures are preferred over static rule sets or self-hosted inference.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T18:46:15.317Z","isFirstParty":false}