ClawHub
Back to skill

Security audit

Duolingo Tracker

Security checks for vulnerabilities and agentic risk

Overview

This Duolingo tracker is a simple disclosed helper for fetching Duolingo stats, though users should treat the optional JWT token like a password.

Before installing, decide whether you are comfortable using an unofficial Duolingo endpoint and optionally providing a Duolingo JWT. Prefer username-only public stats if sufficient, never paste the JWT into chat output or logs, and avoid storing it in shared shell profiles.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrase set includes broad language such as 'how am I doing on Duolingo' and especially 'my language learning progress', which can overlap with generic requests about learning progress outside Duolingo. In an agent environment, this can cause unintended skill invocation, leading the skill to handle unrelated requests and potentially expose or prompt for sensitive Duolingo authentication data in the wrong context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.