ClawHub
Back to skill

Security audit

Pump Fun

Security checks for vulnerabilities and agentic risk

Overview

This skill is openly for Pump.fun crypto trading, but it gives agents direct buy, sell, and token-launch authority with a private key without clear irreversible-transaction warnings or confirmation controls.

Review this carefully before installing. Use only a dedicated Solana trading wallet with limited funds, assume commands may execute real Pump.fun mainnet transactions, and do not provide a private key unless you are comfortable with the agent having authority to buy, sell, or launch tokens. Look for confirmation prompts or dry-run support in the actual runtime before using real funds.

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
Confidence
96% confidence
Finding
The skill exposes direct buy, sell, and token launch commands for a live trading platform, but its command descriptions do not prominently state that invoking them will create real, irreversible on-chain transactions using the configured private key. In an agent context, users may treat these as informational or simulated actions, so insufficient transaction-risk disclosure increases the chance of unintended fund loss or accidental token creation.

Static analysis

No suspicious patterns detected.