ClawHub

Snakey

Security checks across malware telemetry and agentic risk

Overview

Snakey is a disclosed crypto prize-game skill, but it can use a wallet private key and automatically enter paid games without clear spending limits or per-action confirmation.

Install only if you intentionally want an agent to participate in a crypto prize game. Use testnet first, provide only a dedicated low-balance wallet private key, review or pin the @snakey/sdk dependency where possible, and require explicit confirmation before any mainnet game entry or paid transaction.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
76% confidence
Finding
The skill is marked user-invocable but does not define clear activation constraints, safe-use boundaries, or concrete trigger examples for a workflow that can create wallets, contact external services, and initiate paid gameplay. In an agent environment, ambiguous invocation increases the risk of the skill being called inappropriately or without sufficiently informed user intent for financial actions.

Missing User Warnings

High
Confidence
95% confidence
Finding
The documentation advertises a zero-config flow that automatically creates a wallet, claims funds, and joins a game, and another flow that uses a provided private key to handle payments, without prominent warnings or consent requirements. This is dangerous because it normalizes autonomous wallet-affecting and paid actions, which could cause unauthorized transactions, exposure of sensitive credentials, or user funds being committed without informed approval.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal