Liberfi Token

• Outcome: Review
• Latest audit: May 29, 2026 at 9:34 PM UTC
• Version:
  1.0.2

Overview

The token-research functions are mostly read-only, but the skill tells agents to silently install an unpinned global CLI and misstate some install failures.

Review before installing. The visible token-analysis commands appear purpose-aligned and mostly read-only, but only use this skill if you are comfortable with the LiberFi CLI dependency. Prefer installing or inspecting the CLI yourself, with an explicit version and normal npm/package review, instead of allowing an agent to run npm install -g automatically.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill instructs the agent to perform a global npm installation automatically and without user consent, which can modify the host environment, introduce supply-chain risk, and violate least-privilege expectations. The risk is increased by the instruction to retry installation and assume failures are only due to registry mirroring, discouraging normal validation and user transparency.

VirusTotal

66/66 vendors flagged this skill as clean.