Back to skill

Security audit

Masterclass Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local course-building assistant that writes disclosed lesson and progress files, with no hidden code execution or data exfiltration found.

Install if you want workspace-local course files and progress tracking. Use clear course-related requests, and review any suggested cron command before adding scheduled lesson delivery.

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
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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The top-level skill description advertises activation on broad phrases like "I want to learn [topic]" and "next lesson" without exclusions or contextual checks. Because this skill persists data and updates course state, broad activation increases the chance of unintended course creation, lesson generation, or progress modification from ordinary user messages.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger set includes generic phrases like "next lesson" and "continue my course," which are common in normal conversation and are not scoped to this specific skill. That creates a prompt/skill-hijacking risk where the skill may activate unintentionally, causing unexpected file reads/writes in the user's workspace and confusing or unsafe behavior.

Content

No source excerpt is available for this finding.