ClawHub
Back to skill

Security audit

Wallet Overview

Security checks across malware telemetry and agentic risk

Overview

This is a read-only wallet viewing skill that can reveal sensitive wallet details, but its access is disclosed and aligned with its purpose.

Install only if you are comfortable letting the agent query your authenticated fdx wallet account. Ask for scoped results when possible, and avoid showing full addresses, balances, profile details, or transaction history in shared or recorded chats unless you intend to disclose them.

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

Medium
Confidence
90% confidence
Finding
The skill is user-invocable and its description contains broad, everyday trigger phrases like "show my balance" and "what's my address?", which can cause the orchestrator to select it in loosely related conversations. Because the allowed tools retrieve wallet identity, addresses, balances, holdings, and transaction history, accidental invocation can expose sensitive financial data without a clear, deliberate user confirmation step.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill retrieves highly sensitive financial and identity-linked information, including wallet addresses, balances, holdings, and account activity, but it does not instruct the agent to present a privacy warning or obtain explicit user confirmation first. In context, this increases the chance of exposing private wallet data during an ambiguous or incidental request, especially since the skill is broadly invocable and covers multiple chains.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal