Install
openclaw skills install miraix-binance-agent-firewallUse this skill when the user wants to audit a Binance trading prompt, decide whether an AI trader should get Binance account permissions, return Pass/Warn/Block with guardrails, identify allowed/watch-only/blocked symbols, rewrite the prompt into a safer operating mode, or generate a share card URL for the probation report.
openclaw skills install miraix-binance-agent-firewallUse this skill to judge whether an AI trading prompt is safe enough to touch a Binance account. It is backed by Miraix public endpoints and Binance public market data.
Public endpoints:
https://app.miraix.fun/api/binance-agent-firewallhttps://app.miraix.fun/api/binance-agent-firewall/share-imagecurl -sS -X POST https://app.miraix.fun/api/binance-agent-firewall \
-H 'Content-Type: application/json' \
-d '{"prompt":"<raw-trading-prompt>","symbols":["<symbol-1>","<symbol-2>"]}'
Base the answer on the returned JSON. The most important fields are:
statussafetyScoreverdictsummaryfindingsguardrailspermissionPlanprobationProfilesafePromptshareTextIf the user wants the safest possible operating version, prefer safePrompt over inventing a new rewrite.
If the user wants a share card, build a payload with:
statussafetyScoreverdictsummaryprimaryFindingprimaryGuardrailsymbolsdimensionsgeneratedAtThen URL-encode the JSON and append it to:
https://app.miraix.fun/api/binance-agent-firewall/share-image?payload=<urlencoded-json>
shareText and adapt the tone instead of rewriting the whole result from scratch.futuresDataAvailable is false, say funding data was unavailable instead of making it up.