Back to skill

Security audit

Recipe Create Classroom Course

Security checks for vulnerabilities and agentic risk

Overview

This skill is a short Google Classroom recipe whose live course and invitation actions match its stated purpose, with no hidden code or persistence found.

Install only if you intend to use gws with an authorized Google Workspace/Classroom account. Before running the commands, replace the sample course and student values carefully, confirm the target domain and recipient email, and consider using a test course/account first because the commands can create real courses and send real invitations.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill performs live administrative actions against Google Classroom by creating a course and sending an invitation, but it does not clearly warn the user that these actions affect real external resources and may contact a real student account. This increases the risk of accidental misuse, unintended invitations, and unauthorized changes in an education environment.

Static analysis

No suspicious patterns detected.