ClawHub

Liberfi Auth

Security checks across malware telemetry and agentic risk

Overview

This LiberFi login skill is mostly purpose-aligned, but it needs review because it tells agents to install a global CLI without asking and can create persistent authentication files.

Review before installing. Use this skill only if you intend to authenticate with LiberFi, verify the @liberfi.io/cli package yourself, and do not allow a global npm install without explicit consent. Protect ~/.liberfi/session.json and ~/.liberfi/keys/default.json, and understand that local logout may not revoke server-side access.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The skill explicitly instructs the agent to globally install an npm package automatically if the CLI is missing. This expands behavior from authentication into software installation and executes a third-party supply-chain action without user approval, creating risk of unwanted system modification or package compromise.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger list includes broad phrases such as 'verify', 'who am I', 'my account', and 'create account' that may match ordinary user conversation outside the intended skill context. Overbroad invocation can cause the authentication skill to run unexpectedly, increasing the chance of unintended login flows, status checks, or session-affecting actions.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The Chinese trigger list likewise contains generic phrases like 登录, 注册, 验证, and 我是谁 without requiring LiberFi-specific context. This can lead to accidental activation for unrelated Chinese-language requests, especially around identity or account questions, causing unintended auth operations.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal