ClawHub

Andorra

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Andorra travel-planning skill with optional local preference memory and no executable code or network behavior.

Reasonable to install for Andorra trip planning. Decline the preference-memory prompt or avoid sharing sensitive travel details if you do not want trip preferences, budget, group details, or trip history retained in ~/andorra/ or reused later.

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
92% confidence
Finding
The setup instruction says to read this file whenever `~/andorra/` doesn't exist or is empty, which is a broad environmental trigger rather than a tightly scoped user intent. That can cause the skill to activate in unrelated contexts and steer the assistant into Andorra-specific behavior or questioning without clear user consent, increasing the chance of inappropriate context takeover.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill instructs the agent to ask to keep preferences handy and then save the answer to main memory, but it does not provide a clear user-facing notice about what data will be stored, for how long, or how it may be reused. This creates a privacy risk because travel preferences and related personal context could be persistently stored without informed, specific consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal