ClawHub
Back to skill

Security audit

Binance Query Token

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward token-market lookup guide that uses disclosed public API endpoints and does not install code, persist itself, or request credentials.

Install this if you are comfortable with token names, contract addresses, chain choices, and chart parameters being queried against Binance Web3 and the K-Line provider. Avoid using it for wallet-private or strategy-sensitive searches unless you accept that those lookup terms may leave your environment.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill advertises broad activation cues such as token searches, price checks, market data, and candlestick requests without clear scoping or disambiguation rules. That can cause over-invocation on ordinary crypto-related prompts, unnecessarily sending user queries to external services and increasing privacy and prompt-routing risk even when the user did not explicitly ask to use this integration.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill sends user-supplied keywords, contract addresses, and chain selections to third-party endpoints, but the description does not disclose that external transmission will occur. Users may provide sensitive wallet- or research-related identifiers believing the request stays local, creating a transparency and privacy issue and potentially exposing query intent to external providers.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.