ClawHub
Back to skill

Security audit

tonfun

Security checks for vulnerabilities and agentic risk

Overview

This is a simple informational skill for TON.fun that points users to trade or create tokens, but it should add clearer financial-risk warnings.

Before installing or using this skill, treat the listed token and TON.fun instructions as informational rather than an endorsement. Verify contract addresses independently, review wallet prompts carefully, and only risk funds you can afford to lose because on-chain trades can be irreversible and token prices can be highly volatile.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill gives step-by-step instructions for buying, selling, and creating tokens on a blockchain platform without any warning that transactions are financially risky, potentially irreversible, and may expose users to scams, volatility, or permanent loss of funds. In this context, the omission is security-relevant because the content directly encourages on-chain actions by non-expert users, increasing the chance of harmful user decisions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.