Security audit

Quizlet

Security checks for vulnerabilities and agentic risk

Overview

This Quizlet study skill is a narrow Markdown-only helper that stores disclosed local study notes and does not show hidden code execution, network access, credential use, or destructive behavior.

Before installing, be comfortable with the skill keeping local study notes in ~/quizlet/. Review or delete that folder if you do not want exam timelines, study goals, confidence notes, or weak-card patterns retained across sessions.

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

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: 96% confidence
Finding: The Activation section provides placeholders like 'Auto-activate when' and 'Activate only on explicit request for' without any required specificity, examples, or exclusion criteria. In a markdown skill/template file, this creates an ambiguous trigger definition that could lead to inconsistent or unintended invocation behavior.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill explicitly instructs the agent to keep and refresh internal notes in `~/quizlet/memory.md`, which creates persistent storage of user study context, goals, deadlines, and performance patterns without any user-facing notice or consent mechanism. Even though the data is study-related rather than obviously sensitive, it can still include personal schedules, academic weaknesses, and behavioral patterns, and persistence in a home-directory file increases privacy and cross-session data leakage risk.

Static analysis

No suspicious patterns detected.