ClawHub
Back to skill

Security audit

TokenSniff

Security checks across malware telemetry and agentic risk

Overview

TokenSniff is a disclosed crypto-token analysis skill with risky financial-style output, but it does not show hidden code, credential access, wallet control, persistence, or data exfiltration.

Install only if you want speculative crypto-token screening. Verify all market and wallet data independently, avoid treating BUY/WATCH/AVOID labels as financial advice, and do not connect wallets or provide private keys unless a future version clearly scopes and explains that access.

SkillSpector

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

Vague Triggers

High
Confidence
94% confidence
Finding
The trigger criteria are extremely broad and include catch-all language such as "or similar crypto discovery/analysis tasks" and "Always trigger" for broad categories. This can cause the skill to activate outside its intended scope, leading to unnecessary web lookups, overcollection of market/wallet data, and higher risk of the agent producing risky financial-style guidance in contexts where the user did not clearly request this skill.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The skill instructs the agent to track wallets, analyze social/web sources, and inspect on-chain behavior, but it does not include an explicit privacy or data-handling notice. While the data sources are mostly public, wallet-tracking and social-correlation features can still create privacy, profiling, and compliance concerns if users are not warned about the nature and limits of this analysis.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal