ClawHub
Back to skill

Security audit

DOGE节点免费版

Security checks across malware telemetry and agentic risk

Overview

This Dogecoin node skill mostly matches its stated purpose, but it asks for command and write authority while giving inconsistent boundaries around wallet-changing and export-like operations.

Review this before installing if the agent has access to a real Dogecoin wallet. Only use it for local Dogecoin Core node and wallet inspection, avoid generic analytics triggers, and require explicit confirmation before any command that creates addresses, exports data, edits configuration, or could touch wallet state.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Confidence
93% confidence
Finding
The skill claims the free edition is read-only/query-only, but the documented capabilities explicitly include create/export operations and also expose `getnewaddress`, which mutates wallet state by generating new addresses. This mismatch can cause an agent or operator to approve or invoke actions under a false assumption of non-mutating behavior, increasing the risk of unintended wallet changes or future expansion to more sensitive operations.

Intent-Code Divergence

Medium
Confidence
92% confidence
Finding
This is a true security-relevant inconsistency: the same skill describes itself as read-only while advertising create/export capabilities. Contradictory safety boundaries are dangerous in agentic systems because trust decisions, tool routing, and user consent often depend on the declared risk profile rather than the full document.

Vague Triggers

High
Confidence
89% confidence
Finding
The trigger condition says to use the skill for broad data analysis, reporting, statistics, and visualization tasks, which is far wider than its actual Dogecoin-node/RPC scope. Overbroad triggers can cause an agent to activate this exec-capable skill in unrelated contexts, increasing the chance of unnecessary command execution, exposure of wallet/node data, or misuse of local privileges.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.