ClawHub
Back to skill

Security audit

MacClaw Copilot CLI

Security checks for vulnerabilities and agentic risk

Overview

This is a small Copilot CLI helper, but it instructs use of a local GitHub Copilot token without enough credential-safety guidance.

Review this before installing if you are uncomfortable with skills that reference local tokens. Only use it if the GitHub Copilot token file has restrictive permissions, avoid logging or sharing the command output/environment, and prefer the official CLI authentication flow when available.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The manifest description and body text are written in Chinese, indicating a fixed language experience, but the file does not state that the skill is intended specifically for Chinese-speaking users or offer any language choice. Per policy, language constraints should be opt-in or clearly justified as region- or audience-specific.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs users to load a GitHub Copilot token directly from a local file into an environment variable without any warning about credential sensitivity, storage protections, shell history, or process exposure. This creates a real credential-handling risk because users may normalize unsafe token usage patterns and accidentally expose the token through logs, screenshots, shared terminals, or weak file permissions.

Static analysis

No suspicious patterns detected.