ClawHub
Back to skill

Security audit

GitHub Trending Skill

Security checks across malware telemetry and agentic risk

Overview

This skill fetches public GitHub Trending pages and summarizes them in Chinese, with only small local caching and no credential or destructive behavior found.

Install if you are comfortable with the skill making live requests to GitHub and storing small cache files of public trending results. Treat any fetched repository descriptions as untrusted web content rather than instructions for your agent.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill declares executable scripts that perform network access and likely use file I/O for caching, but it does not declare any permissions. This creates a transparency and policy-enforcement gap: hosts or reviewers may approve the skill without understanding that it can fetch remote content and read/write local data, increasing the risk of unintended data access or unsafe execution.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.