ClawHub
Back to skill

Security audit

Cue Margin Trading

Security checks across malware telemetry and agentic risk

Overview

The skill is coherent for Cue-based margin-trading research, but it asks the agent to fetch and run unpinned remote code that can use a local Cue API key.

Review this before installing if you are not comfortable with a skill updating code under ~/.cue and running it with access to your Cue account credentials. Prefer using a trusted, pinned runner version and confirm what will be installed before the first run.

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 (2)

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The skill directs the agent to clone or update a remote Git repository into the user's home directory and then execute code from that checkout. This expands the skill from passive research into arbitrary remote code retrieval and execution, creating a supply-chain risk if the repository, mirror, branch, or transport path is compromised.

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The skill explicitly relies on a local API key stored under ~/.cue/config.json and tells the agent the runner will read it automatically. Accessing credentials from the user's home directory is a sensitive capability not inherent to margin-trading research and could expose or misuse secrets if the runner or surrounding workflow is compromised.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal