Miraix Binance Agent Firewall
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill is transparent about sending Binance trading prompts to a Miraix audit API and does not request credentials or account access.
This skill appears coherent and instruction-only. Before installing, understand that it works by sending the trading prompt you provide to Miraix public endpoints; do not include Binance API keys, withdrawal permissions, balances, personal data, or proprietary strategy details unless you are comfortable sharing them with that service.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A trading prompt may contain sensitive strategy or operational details, so that content would be shared with the Miraix API.
The skill explicitly sends the user's trading prompt and symbols to an external provider endpoint for scoring.
curl -sS -X POST https://app.miraix.fun/api/binance-agent-firewall ... -d '{"prompt":"<raw-trading-prompt>","symbols":["<symbol-1>","<symbol-2>"]}'Use only prompts you are comfortable sharing with the external service, and remove API keys, balances, personal identifiers, or private account information before auditing.
If a user asks for a Binance trading-prompt audit, the agent may call the Miraix endpoint as part of fulfilling that request.
The skill allows an agent to invoke it when the task appears to match, which may trigger the documented external audit workflow without the user manually selecting the skill each time.
policy: allow_implicit_invocation: true
Confirm that external API use is acceptable before pasting sensitive trading prompts, and ask the agent not to call external services if you want a local-only review.