ClawHub
Back to skill

Security audit

Launch a Token

Security checks for vulnerabilities and agentic risk

Overview

This skill appears purpose-built for launching Solana tokens, but it involves real wallet signing and irreversible on-chain financial actions without enough built-in caution or confirmation guidance.

Review this before installing if you plan to use a real wallet. Use a dedicated low-balance wallet, verify the active wallet address and network before every transaction, keep the keypair file out of chat and logs, and require explicit confirmation before creating or finalizing a launch because these actions can spend SOL and publish irreversible on-chain state.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill guides users through creating and finalizing a token launch, which triggers real on-chain transactions, spends SOL, uploads metadata, and can create liquidity pools with effects that are costly or impossible to reverse. Without an explicit warning and confirmation step, users may treat this like a harmless informational workflow and accidentally authorize irreversible financial actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructs users to provide a Solana keypair path and even suggests a default private key location, but does not include a strong warning that this path points to highly sensitive signing material. In an agent setting, normalizing direct use of wallet key files increases the risk of credential exposure, misuse of a hot wallet, or unintended signing with a default key the user did not mean to use.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.