ClawHub
Back to skill

Security audit

B.Fun AI

Security checks for vulnerabilities and agentic risk

Overview

Review is advised because the skill is a disclosed crypto wallet helper, but it relies on an unpinned external npm CLI that can use a private key for irreversible BSC transactions.

Install only after verifying the npm package and source repository, and prefer a pinned version rather than @latest. Use a dedicated low-balance wallet, never paste private keys or seed phrases into chat, confirm every address, amount, slippage, network, and token before signing, and treat token creation images and metadata as data that will be uploaded externally.

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
91% confidence
Finding
This markdown file states that the flow uploads token metadata and image to the B.Fun backend, may approve collateral, and sends a factory transaction, but it does not explicitly warn readers about privacy implications or the irreversible nature of blockchain/state-changing operations. Although the operator checklist mentions user approval for write operations, it does not disclose backend data transmission or clearly warn about consequences such as public on-chain actions and token approvals.

Static analysis

No suspicious patterns detected.