Open Courses

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:24 PM UTC
• Version:
  0.1.1

Overview

This is a lightweight instruction-only course guide with no code, install steps, credentials, persistence, or system access requested.

Safe to install as a course-selection prompt guide. Treat course prices, discounts, certificates, and instructor claims as information to verify on the official platforms, and avoid sharing account credentials or private education records unless you explicitly intend to.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 76% confidence
• Finding: The sample trigger phrases are extremely broad and generic, making it more likely that ordinary user requests will unintentionally invoke this skill. In an agent system, overbroad invocation patterns can cause prompt/skill hijacking at the routing layer, leading the assistant to answer from the wrong capability domain or surface unintended content.

VirusTotal

63/63 vendors flagged this skill as clean.