Github Agent Trends

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:29 PM UTC
• Version:
  1.0.0

Overview

This skill is a read-only GitHub trend-reporting helper; its network and optional token use are disclosed and fit its purpose.

Install this if you want an agent to run GitHub trend leaderboards. Use a low-privilege GitHub token only if needed for rate limits, and invoke the skill intentionally because it will run a local Python script and contact GitHub.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 86% confidence
• Finding: The skill instructs the agent to run a Python script that uses network access to query the GitHub Search API and can read a GitHub token from the environment, yet the skill declares no permissions or safety constraints. This creates a real transparency and policy-enforcement gap: an agent may perform outbound requests and access sensitive environment data without explicit user-facing authorization boundaries.

VirusTotal

66/66 vendors flagged this skill as clean.