ClawHub
Back to skill

Security audit

TronScan Contract Analysis

Security checks across malware telemetry and agentic risk

Overview

This is a read-only TronScan contract analysis skill with minor routing ambiguity but no hidden code, persistence, or destructive behavior.

Install this if you are comfortable with TRON contract or address queries being sent to the disclosed TronScan MCP service. For token-holder, token-supply, or account-balance questions, use the more specific token or account skills to avoid ambiguous routing.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
Using any provided contract address as an activation trigger is overly broad and can cause the agent to invoke this skill in contexts where the user did not request contract analysis. That increases the chance of incorrect tool selection, unnecessary external data access, and leakage of user intent or queried addresses to the MCP service.

Vague Triggers

Medium
Confidence
87% confidence
Finding
Generic 'Use when' phrases like 'contract info', 'contract address', or 'recent calls' can overlap with other skills and cause ambiguous routing. In an agent environment, such ambiguity can lead to the wrong tool being selected, data being fetched from an external MCP unnecessarily, or results being presented outside the intended scope.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal