Glovo

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Glovo ordering helper that can use a signed-in browser and optional local notes, but its sensitive actions are bounded by approval and checkout safeguards.

Install only if you want an agent helping inside your real Glovo session. Keep browser-control permission explicit, review address/cart/payment summaries yourself before confirming, and allow ~/glovo/ memory only for non-sensitive preferences you are comfortable storing locally.

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: 86% confidence
Finding: The setup instructions define activation in broad terms and defer the real boundary-setting until later questions, which can cause the skill to engage on loosely related Glovo mentions before the user has clearly consented to browser use or cart-related actions. In a commerce context tied to live sessions, addresses, and ordering state, ambiguous triggering increases the chance of unintended data access or actions.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill instructs storage of persistent user data including activation preferences, neighborhoods, address labels, and shopping habits in a local memory file without clearly informing the user that this data will be retained. Even without passwords or payment details, this creates privacy risk because address-related and behavioral data can reveal location, routines, and purchasing patterns across sessions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal