ClawHub
Back to skill

Security audit

MacClaw Copilot CLI

Security checks across malware telemetry and agentic risk

Overview

The skill appears purpose-aligned for GitHub Copilot CLI use, but its token-handling example needs careful secret hygiene.

Install only if you are comfortable letting the skill use your GitHub Copilot token. Treat that token as a secret: prefer an official login flow, OS keychain, or environment variable over plaintext files and avoid commands that expose tokens in shell history or process arguments.

SkillSpector

By NVIDIA
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 (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The usage example reads a GitHub token directly from a local file and injects it into the command line without any warning about credential sensitivity, storage hygiene, or exposure risks. This can normalize insecure secret-handling practices, such as leaving long-lived tokens in plaintext files or exposing them via shell history, process inspection, screenshots, or copied commands.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.