GitHub Projects Explorer

• Outcome: Pass
• Latest audit: May 28, 2026, 4:45 AM
• Version:
  1.0.6

Overview

This skill appears to be a straightforward GitHub repository search helper, with the main caution being careful handling of an optional GitHub token.

Safe to use for discovering public GitHub repositories. If you configure GITHUB_TOKEN, treat it as a secret, use the minimum permissions needed, avoid private-repository or write scopes, and prefer a temporary environment variable or secret manager over saving it permanently in ~/.zshrc.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The instructions tell users to store a GitHub token permanently in ~/.zshrc without warning about credential sensitivity, scope minimization, or risks from shell history, local compromise, and accidental disclosure. While not an exploit by itself, it encourages insecure secret-handling practices that can lead to long-lived credential exposure if the machine, dotfiles, or logs are accessed.

Missing User Warnings

Low

• Confidence: 83% confidence
• Finding: The documentation shows authenticated GitHub API usage with an `Authorization: token YOUR_TOKEN` header but does not include any guidance about protecting tokens from shell history, logs, screenshots, or source control. In an agent skill context, users may copy examples directly, increasing the chance that real credentials are embedded unsafely or exposed during troubleshooting.

VirusTotal

65/65 vendors flagged this skill as clean.