ClawHub
Back to skill

Security audit

Github repository quickstart

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused GitHub repository onboarding helper that uses a declared GitHub MCP service and does not show hidden execution, persistence, or destructive behavior.

Install this if you are comfortable with a GitHub MCP service being used to inspect repositories you ask about. Be more cautious with private repositories because repository metadata and file contents needed for analysis may be sent to or retrieved through the declared GitHub MCP integration.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Content
value: "github"
      description: "GitHub MCP server for repository structure, releases, and maintenance checks"
      transport: "streamable_http"
      url: "https://api.githubcopilot.com/mcp/"

policy:
  allow_implicit_invocation: true
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill enables implicit invocation without any explicit trigger constraints in the policy block, which can cause the agent to activate this skill in situations broader than intended. Because the skill also reaches out to an external GitHub MCP service, over-broad activation increases the chance of unnecessary external calls and unintended repository analysis based on ambient user context.

Static analysis

No suspicious patterns detected.