ClawHub
Back to skill

Security audit

Binance Sports Ai Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Binance sports prediction assistant that fetches public match analysis and only hands off trading after explicit user confirmation.

Before installing, understand that the skill can show AI-generated sports and market analysis and can guide a Binance Agentic Wallet prediction-market trade. Do not treat its output as financial advice, and only proceed with wallet commands after checking the selected outcome, amount, quote, slippage, and confirmation prompt.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill clearly instructs the agent to call external endpoints and perform trading-related handoffs, but it does not declare any explicit tool scope such as allowed tools or permissions. That mismatch weakens least-privilege boundaries and can let the skill be invoked with broader network/tool access than users or the platform expect, increasing the blast radius if the skill or upstream data is abused.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The invocation description is broad enough to match general World Cup news, predictions, analysis, and even trading-adjacent queries, which can cause the skill to activate in situations beyond its narrow intended use. Over-broad triggering is risky here because the skill drives network lookups, presents AI-generated betting analysis, and may steer users toward a wallet trading flow, so accidental invocation meaningfully increases exposure.

Content

No source excerpt is available for this finding.