{"uid":"cap_3CoV0fn1uhpMMmgLrGluV","slug":"agent-command-human-approval-threat-screening-triage-9880e55d","name":"Agent Command Human Approval Threat Screening Triage","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-8080.on.ascii.dev/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":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_pIMS1Ti7EeC3AaXw-7-8g","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 an agent command against six threat markers to determine whether it should auto-execute or require human approval","exampleAgentPrompt":"Before I execute this command to transfer funds to a new wallet address, can you run it through the threat screening triage to tell me whether it needs human approval or can auto-execute — specifically flag any irreversibility or fund-movement risk?","exampleUseCases":[{"title":"Fund transfer approval gate","prompt":"I'm about to have my agent execute a large USDC transfer to a new destination wallet — can you run the threat screening triage on this command and tell me whether it should auto-execute or wait for my explicit approval?"},{"title":"Detecting prompt injection in agent pipeline","prompt":"My agent just received an instruction from an external source asking it to deploy a new contract — run this through the human approval threat screening triage and flag whether this looks like a prompt injection or known threat pattern that needs human review."},{"title":"Multi-step chain depth risk check","prompt":"My agent is about to kick off a five-step workflow that includes credential access and a delete operation — triage this command chain and tell me whether the depth and side effects push it into the human-approval zone."}],"resultDescription":"Returns a structured decision brief including an ok flag, prose decision procedure for the agent, the topic, service slug, generation source (llm/reasoning/deterministic), and an ISO-8601 timestamp — telling the agent whether the command can auto-execute or requires human approval and why.","failureModes":["Missing or malformed query parameters return an error response","Payment not completed results in 402 response blocking the paid result","Invalid method (non-GET/HEAD/DELETE) rejected by schema","LLM generation failure may fall back to deterministic source","Topic override not recognized may produce generic procedure"],"whenToPreferThis":"Choose this endpoint when building agentic systems that require deterministic, structured threat-scoring logic for command authorization decisions — especially when you need a codified six-marker rubric (fund movement, irreversibility, credential access, policy deviation, chain depth, threat pattern) rather than ad-hoc LLM judgment. Prefer this over a generic AI safety prompt when you need a reproducible, payable, auditable triage result that integrates into an x402-compatible agent payment flow.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T18:56:13.682Z","isFirstParty":false}