Binance Square Post

Security checks across malware telemetry and agentic risk

Overview

The skill appears purpose-built for Binance Square posting, but it handles credentials and public posting authority without enough clear confirmation and safety guidance.

Review before installing. Only use it with a Binance key you are comfortable granting posting authority to, store that key as a secret, and require the agent to show the exact final post and wait for your explicit confirmation before publishing anything to Binance Square.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README instructs users to place a Binance Square OpenAPI key into configuration without any warning that the key is sensitive or guidance on secure storage. In an agent-skill context, users may paste live credentials into files, prompts, logs, or version control, increasing the chance of accidental disclosure and unauthorized posting through their account.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The documentation tells users to send content to Binance Square and provides a posting example, but does not clearly warn that content is transmitted to a third-party external service and may become publicly visible. In this skill's context, that omission can lead users to unknowingly publish sensitive, proprietary, or personal information.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The example trigger phrases are broad enough that normal conversational requests like '帮我发一条关于 $BTC 行情分析的帖子' or '生成并发布今日新闻简报' could activate a high-impact action: publishing content to a public social platform. Because this skill performs external side effects, ambiguous invocation increases the risk of unintended posting, reputational harm, and accidental use of stored API credentials.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documents automatic news fetching from third-party APIs and subsequent publication to Binance Square, but it does not prominently require informed user consent for outbound data transfer and public posting. Users may believe they are only generating a summary locally when the workflow actually sends requests to external services and posts content publicly, creating privacy, compliance, and unintended-publication risks.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal