{"domain":"agentpass-protocol.rmalka06.chatgpt.site","count":1,"changes":[{"captured_at":"2026-09-22T02:42:59","card_hash":"a0cece438c07109b66c0d8354329dda39e17b772fe52735a50217ad2f59d448f","previous_card_hash":null,"diff":{"skills_added":[{"id":"intentfence-action-authorization","name":"Fail-closed agent action authorization","description":"Bind an exact MCP, HTTP, A2A, or payment action to an allowlist, cost ceiling, retention ceiling, and optional action-specific human approval. Returns a five-minute ES256 receipt and never executes the action.","tags":["agent-security","authorization","policy-enforcement","MCP","signed-receipt"],"inputModes":["application/json","text/plain"],"outputModes":["application/json","text/plain"]},{"id":"intentfence-agent-checkout","name":"Budget-capped agent checkout","description":"Choose an IntentFence paid outcome and receive the exact endpoint, validated input, Coinbase Agentic Wallet MCP request, Agentic Wallet argv, proactive x402 MCP tool call, and Base USDC ceiling without signing or initiating payment.","tags":["agent-commerce","x402","MCP","Base","USDC","spend-control"],"inputModes":["application/json","text/plain"],"outputModes":["application/json","text/plain"]},{"id":"intentfence-agent-risk-scan","name":"MCP metadata risk scan","description":"Scan caller-supplied MCP tool definitions for missing schemas, conflicting annotations, absent approval binding, and missing cost boundaries without executing tools.","tags":["MCP","agent-security","risk-scan","tool-metadata"],"inputModes":["application/json","text/plain"],"outputModes":["application/json","text/plain"]},{"id":"intentfence-preflight","name":"Agent payment preflight","description":"Evaluate caller-declared payment intent and return safe_to_proceed, needs_review, or denied before the caller invokes its downstream tool. IntentFence does not independently authorize or execute the action.","tags":["declared-input-policy","policy","safety","audit","preflight","x402","USDC"],"inputModes":["application/json","text/plain"],"outputModes":["application/json","text/plain"]},{"id":"intentfence-production-policy-pack","name":"Self-service production policy pack","description":"Generate a runtime-specific fail-closed TypeScript guard, signed action and policy receipt, negative test vectors, and deployment checklist for 1 USDC through x402.","tags":["authorization","Cloudflare Agents","Coinbase AgentKit","OpenAI Agents SDK","MCP","x402"],"inputModes":["application/json","text/plain"],"outputModes":["application/json","text/plain"]},{"id":"intentfence-screen-base-wallet","name":"Screen every Base recipient before payment","description":"Run a live Base wallet-risk screen for 0.002 USDC before paying a new recipient, using one budget-capped x402 call and a fail-closed signed result.","tags":["wallet-risk","Base","USDC","x402","agent-commerce","repeat-purchase"],"inputModes":["application/json","text/plain"],"outputModes":["application/json","text/plain"]},{"id":"intentfence-x402-assessment","name":"Caller-observed x402 quote assessment","description":"Validate and sign the exact PAYMENT-REQUIRED quote observed by the caller against a Base USDC ceiling, explicit payee allowlist, timeout, and resource binding. IntentFence never fetches or pays the target.","tags":["x402","merchant-risk","payment-safety","quote-assessment","USDC"],"inputModes":["application/json","text/plain"],"outputModes":["application/json","text/plain"]},{"id":"intentfence-x402-readiness","name":"Live x402 endpoint readiness","description":"Make one bounded credential-free request to a public HTTPS endpoint, block redirects and private-network targets, validate its live x402 challenge, and return a signed receipt without paying the target.","tags":["x402","endpoint-readiness","payment-safety","SSRF","USDC"],"inputModes":["application/json","text/plain"],"outputModes":["application/json","text/plain"]}],"skills_removed":[],"skills_changed":[],"fields_changed":[{"field":"name","before":null,"after":"IntentFence Policy Agent"},{"field":"description","before":null,"after":"Authorizes exact autonomous-agent actions against explicit policy, returns short-lived signed receipts, and scans MCP tool metadata for high-risk gaps."},{"field":"version","before":null,"after":"0.16.0"},{"field":"supportedInterfaces","before":null,"after":[{"url":"https://agentpass-protocol.rmalka06.chatgpt.site/a2a","protocolBinding":"HTTP+JSON","protocolVersion":"1.0"}]},{"field":"capabilities","before":null,"after":{"streaming":false,"pushNotifications":false}}],"other_changed":true,"is_empty":false,"human_summary":"added 8 skills · name ∅ → IntentFence Policy Agent · description ∅ → Authorizes exact autonomous-agent action · version ∅ → 0.16.0 · supportedInterfaces ∅ → https://agentpass-protocol.rmalka06.chat · capabilities ∅ → none"}}]}