ClawHub
Back to skill

Security audit

Github Explorer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a GitHub search and repository analysis helper with disclosed GitHub API use, optional token use, and local caching.

Install if you are comfortable sending GitHub search terms and repository names to GitHub and storing short-lived search or README cache files locally. Use a least-privilege GitHub token, ideally read-only/public access, and use --no-cache or cache clear when you do not want results retained locally.

SkillSpector

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 only a persistence permission for its cache, but the content clearly instructs use of environment variables, local file cache access, and outbound network calls to the GitHub API. This mismatch weakens permission transparency and can cause the platform or user to underestimate what the skill can access and transmit, especially since user queries and repository names are sent externally and cached locally.

Static analysis

No suspicious patterns detected.