ClawHub
Back to skill

Security audit

Cue Overseas Expansion

Security checks across malware telemetry and agentic risk

Overview

This is a real Cue research skill, but it fetches and runs live remote code that can use your local Cue account key.

Review before installing if you are not comfortable with a skill updating code under ~/.cue and running it with access to your Cue account. Prefer a pinned, reviewed runner version, inspect the repository before first use, and confirm credit-spending runs explicitly.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The skill instructs the agent to clone or update a remote Git repository and then execute a Python script from that repository on the local system. That creates a software supply chain risk and expands the skill's effective permissions far beyond document-based research: a compromised upstream repo, mirror, or account could deliver arbitrary code for execution, potentially exposing local files, credentials, or enabling further system compromise.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal