Github repository quickstart

• Outcome: Review
• Latest audit: May 29, 2026 at 9:26 PM UTC
• Version:
  1.0.0

Overview

The skill appears aimed at GitHub repository help, but its broad automatic activation is under-scoped for a tool that can contact an external GitHub MCP service.

Review before installing. Use it only if you want GitHub MCP-assisted repository analysis, keep any GitHub token or session limited to the minimum repositories and scopes needed, and prefer disabling implicit invocation or requiring confirmation before external GitHub lookups.

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 (2)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The trigger conditions are broad enough to activate on many generic repository-help requests, which can cause the agent to invoke this skill outside its narrowly intended scope. Over-broad activation increases the chance of inappropriate tool use, unnecessary repository inspection, and incorrect task routing, especially when a user only wants lightweight advice rather than structured repo analysis.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The skill enables implicit invocation without defining any narrow trigger constraints, exclusions, or confirmation requirements. Because this skill can contact an external GitHub MCP service, broad auto-invocation increases the chance it will be triggered in contexts the user did not clearly intend, causing unintended repository lookups and data transmission.

VirusTotal

65/65 vendors flagged this skill as clean.