ClawHub
Back to skill

Security audit

LeSecure Local/On-Prem

Security checks across malware telemetry and agentic risk

Overview

The skill appears to expose a location lookup through broad trigger phrases, which could request sensitive GPS data when the user did not clearly intend to use this skill.

Review the skill carefully before installing. Only use it if you are comfortable with it requesting device location, and prefer a version that requires explicit LESecure/location intent plus confirmation before any GPS lookup.

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 (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill registers very broad triggers for location queries such as "current location" and "where am i," which can cause this skill to activate for generic user requests unrelated to encryption. Because the skill then instructs the agent to run `LE -7`, a privacy-sensitive GPS query, unintended routing could expose or request device-location access in contexts where the user did not specifically intend to use this tool.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.