GitHub Trending Feed

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:26 PM UTC
• Version:
  1.0.0

Overview

This skill fetches public GitHub Trending repository data and prints JSON, with no local data access, credential use, persistence, or account-changing behavior found.

Install only if you are comfortable with the skill making unauthenticated requests to GitHub. Treat results as best-effort: if scraping fails it may return fallback repositories, and the language-filter option may not work as described.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• 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

Findings (2)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 89% confidence
• Finding: The skill clearly requires outbound network access to fetch GitHub Trending data and call the GitHub REST API, but it does not declare any permissions. Undeclared network capability weakens review and enforcement because operators may approve or run the skill without understanding its true access needs, increasing the chance of unauthorized external communication.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 81% confidence
• Finding: The description says the skill fetches GitHub Trending repositories, but the workflow also performs additional GitHub REST API calls for each repository to collect more details. This behavior gap matters because extra API calls expand network activity, data flow, rate-limit exposure, and operational risk beyond what a reviewer or user would reasonably infer from the declared purpose.

VirusTotal

66/66 vendors flagged this skill as clean.