Back to skill

Security audit

gurkerlcli

Security checks across malware telemetry and agentic risk

Overview

This is a coherent grocery-shopping helper for Gurkerl, with disclosed account access, but users should avoid storing the account password in plaintext files.

Install only if you want an agent to help with a live gurkerl.at account. Prefer the secure login/keychain flow, avoid putting your password in ~/.env.local or shell profiles, and review before letting the agent add, remove, clear, create, or delete cart/list items.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger terms are broad enough to activate on generic shopping or grocery-related requests, which can route users into a capability that operates on a real third-party account. In this skill, unintended activation is more dangerous because the documented commands can inspect account data, modify carts, and use stored credentials, increasing the chance of unauthorized or surprising actions.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The authentication and command sections describe use of live account credentials and persistent session storage, but they do not prominently warn that commands can modify a real shopping cart or that credentials may be stored in environment files. In this context, the omission is risky because users may unknowingly authorize actions against their account or place secrets in less secure locations such as ~/.env.local.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.