币安热点编辑部

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:22 PM UTC
• Version:
  1.0.1

Overview

This is a narrowly scoped Binance market-content drafting skill that uses disclosed hosted APIs and does not request credentials, local access, trading authority, or publishing authority.

Reasonable to install as an editorial drafting aid. Treat its output as market commentary, verify facts before publishing or acting on it, and do not include private account, wallet, trading, or portfolio information in requests sent to the hosted API.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill instructs use of remote APIs but never clearly warns that request contents and any user-supplied parameters may be transmitted to an external service. That creates a privacy and data-handling risk because users or calling agents may send prompts, symbols, watchlists, or other contextual data off-platform without informed consent.

Natural-Language Policy Violations

Medium

• Confidence: 83% confidence
• Finding: The description says the skill generates Binance Square Chinese drafts, which strongly biases output language without indicating that this is optional or user-selectable. This is primarily a user-consent and expectation issue rather than a direct exploit, but it can cause unwanted disclosure or miscommunication if the user expected another language.

VirusTotal

65/65 vendors flagged this skill as clean.