Liberfi Market

• Outcome: Review
• Latest audit: May 29, 2026 at 9:35 PM UTC
• Version:
  1.0.3

Overview

This skill performs read-only token market lookups, but it tells the agent to install a global npm CLI without asking and to give a predetermined explanation for install failures.

Review before installing. Use this only if you are comfortable with an agent installing `@liberfi.io/cli` globally from npm; preferably install and verify the CLI yourself, require approval before any install or retry, and do not provide wallet credentials or approve transactions when using this market-ranking skill.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Context-Inappropriate Capability

Medium

• Confidence: 97% confidence
• Finding: The skill directs the agent to perform a global npm install automatically for a read-only discovery task, expanding system state and trust without necessity or user consent. Installing packages from a registry introduces supply-chain and environment-modification risk, especially because the instruction normalizes retrying installation rather than failing safely.

Missing User Warnings

High

• Confidence: 99% confidence
• Finding: The skill explicitly instructs automatic global CLI installation without warning or consent, which is a high-risk action because it modifies the host environment and trusts a remote package source. In an agent setting, this can be exploited to trigger unauthorized software installation and expose users or systems to supply-chain compromise.

VirusTotal

64/64 vendors flagged this skill as clean.