ClawHub
Back to skill

Security audit

trongrid-token-scanner

Security checks for vulnerabilities and agentic risk

Overview

This skill provides disclosed TRON token due-diligence instructions using public blockchain data and supplemental web lookups, with no hidden execution, persistence, or credential handling found.

Before installing, understand that the skill may use public web results as supplemental evidence for token safety and market context. Treat community scam reports and search results as unverified signals, not definitive proof, and avoid sharing private wallet credentials or seed phrases because this skill does not need them.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (1)

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The example workflow instructs the agent to perform a general web search for scam reports, which extends behavior beyond the declared TRON on-chain analysis capability set. This creates a scope-expansion path where the agent may rely on untrusted off-platform content, produce inconsistent results, or invoke undeclared browsing capabilities that are not governed by the skill’s manifest and trust boundaries.

Static analysis

No suspicious patterns detected.