ClawHub
Back to skill

Security audit

Nano (XNO)

Security checks across malware telemetry and agentic risk

Overview

This is a real Nano wallet helper, but it can automatically broadcast receive/open transactions and may activate on generic wallet or balance requests.

Install only if you want an agent to work with Nano/XNO wallets. Before use, require explicit confirmation for any send, refund, receive/open, representative change, or spending-limit/config change, and be careful with generic requests like wallet, balance, invoice, or open account. Do not share seeds or private keys with the agent.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list includes very broad terms such as 'wallet', 'wallets', 'balance', 'qr code', 'invoice', 'refund', 'send back', and 'transaction analysis', which can match many unrelated user requests. In an agent environment, this can cause the Nano skill to activate outside its intended scope and steer the assistant into blockchain or wallet operations when the user meant something else, increasing the chance of unsafe actions or confused delegation.

Missing User Warnings

High
Confidence
98% confidence
Finding
The skill explicitly instructs the agent to call 'wallet_receive' immediately whenever pending funds are detected, without first obtaining explicit user confirmation that a blockchain transaction should be broadcast. Receiving funds on Nano is an on-chain state-changing action, so automatic execution can violate user intent, create unexpected ledger activity, and normalize autonomous financial operations by the agent.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
90% confidence
Finding
The trigger phrase 'open account' overlaps with common built-in or generic assistant intents involving opening an account, and the analyzer notes a conflict with a built-in 'open' command. This shadowing can misroute ordinary account-opening requests into a cryptocurrency wallet skill, especially because the skill also contains state-changing wallet instructions.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.