{"uid":"cap_KLyM-9G6fZ1UvcXgv7pqO","slug":"pre-human-agent-command-threat-screening-procedure-3ccffd6a","name":"Pre-Human Agent Command Threat Screening Procedure","description":"Decision procedure that scores a proposed agent command for risk before it reaches a human approver: classifies commands (read-only, fund-moving, data-exfiltration, irreversible), scores each by blast radius and novelty, routes low-risk to auto-allow and high-risk to a human with a three-bullet evidence summary, caps the human approval queue to prevent fatigue, and recalibrates thresholds from weekly missed-threat audit. Addresses the quantified failure where humans miss one in three threats","url":"https://k2so-8080.on.ascii.dev/api/services/pre-human-agent-command-threat-screening-automat","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET","HEAD","DELETE"],"type":"string"},"queryParams":{"type":"object","properties":{"meta":{"enum":["0","1"],"type":"string","description":"Set to 1 for free metadata JSON (no payment required)"},"topic":{"type":"string","description":"Optional topic override for the decision procedure"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","title":"Pre-human agent command threat screening procedure paid response","$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":null,"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_6oTBkBhb16gHEDSG54Syp","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":"Scores and classifies a proposed agent command for risk before it reaches a human approver, routing low-risk commands to auto-allow and high-risk ones to a human review queue with evidence summaries.","exampleAgentPrompt":"Before I let this agent command go through, screen it for risk — classify whether it's read-only, fund-moving, data-exfiltration, or irreversible, score its blast radius and novelty, and tell me if it should be auto-approved or escalated to a human with an evidence summary.","exampleUseCases":[{"title":"Screening a fund-moving agent action","prompt":"I have an autonomous agent about to execute a payment transfer command — screen it for risk first and tell me whether it should be auto-approved or held for my review with a summary of why it's dangerous."},{"title":"Preventing human approval queue fatigue","prompt":"My team is getting overwhelmed with agent command approvals — can you score these proposed commands so only the truly high-risk ones reach the human queue, and the routine read-only ones get auto-allowed?"},{"title":"Post-incident command novelty check","prompt":"An agent just proposed an unusual command I've never seen before — run it through the threat screening procedure to score its novelty and blast radius before I decide whether to approve it."}],"resultDescription":"Returns a decision procedure brief (`brief`) with a risk classification (read-only, fund-moving, data-exfiltration, or irreversible), blast radius and novelty scores, a routing decision (auto-allow or escalate to human), and a three-bullet evidence summary for human reviewers. Also includes service metadata, generation source, and an ISO-8601 timestamp.","failureModes":["Missing or malformed `input` object returns a schema validation error","Unsupported HTTP method (e.g. POST) rejected by enum constraint","Unpaid request without x402 payment returns 402 Payment Required","LLM generation failure may return a degraded or empty `brief` field","Topic override not recognized may fall back to default classification logic"],"whenToPreferThis":"Choose this endpoint when you need automated pre-screening of agent commands before they reach a human approver — especially in high-volume agentic workflows where human fatigue leads to missed threats. Prefer this over generic risk APIs when you need command-class-specific scoring (read-only vs fund-moving vs irreversible), blast radius estimation, and queue management logic tuned for agentic oversight contexts.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T18:59:50.833Z","isFirstParty":false}