ClawHub
Back to skill

Security audit

Hodl Dance Skill

Security checks across malware telemetry and agentic risk

Overview

This skill appears purpose-built for HODL.DANCE trading, but it can immediately spend real crypto funds and approve token transfers without enough confirmation safeguards.

Install only if you intentionally want an agent or CLI to trade and launch tokens from a real BSC wallet. Use a low-balance dedicated wallet, quote first, manually verify contract addresses and amounts, and do not allow buy, sell, approve, or create commands to run unattended.

SkillSpector

By NVIDIA
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 (3)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The README advertises `buy-token`, `sell-token`, and `create-token` commands and instructs users to export `HODL_PRIVATE_KEY`, but it does not clearly warn that these are real on-chain actions that can spend funds, trigger approvals, and create irreversible transactions. In an agent skill context, this omission is more dangerous because autonomous systems may treat README examples as safe defaults and execute them without adequate human confirmation or risk controls.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill documents live on-chain buy/sell and token-creation commands that can spend real funds and trigger irreversible transactions, but it does not place a prominent explicit risk warning in the transaction-executing sections. In an agent context, this increases the chance that a user or autonomous workflow will treat the commands as routine operations and execute speculative trades without understanding slippage, approval risk, gas costs, scams, or permanent financial loss.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
This command performs a state-changing blockchain transaction immediately after parsing CLI arguments, with no explicit confirmation, dry-run gate, or slippage/maximum-spend protection before sending BNB. In a high-risk context like token purchasing, a typo, bad copied address, manipulated automation input, or misunderstood amount can cause irreversible loss of funds because on-chain transactions cannot be rolled back.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/build.js:39