Duolingo Tracker

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Duolingo stats helper, but users should handle the optional Duolingo browser token like a password.

Prefer username-only mode unless you need private stats. If you use DUOLINGO_JWT, store it only in a trusted local secret or environment, never paste it into chat or screenshots, and refresh your Duolingo session if the token may have been exposed.

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: 88% confidence
Finding: The trigger phrase set includes broad language like "my language learning progress," which can match general educational or productivity requests not specifically about Duolingo. This can cause the skill to activate in unintended contexts and prompt for or use a sensitive Duolingo JWT token when the user did not explicitly request Duolingo-related access.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal