ClawHub
Back to skill

Security audit

Take Back My Latte

Security checks across malware telemetry and agentic risk

Overview

This skill locally analyzes user-provided OpenAI cost and usage JSON files and does not show hidden upload, credential, persistence, or destructive behavior.

Before installing, understand that you will be providing local OpenAI usage or cost exports to the agent for analysis. The artifact is designed to avoid API keys and uploads, but those exports may still contain project, model, request, or billing details, so only run it on files you are comfortable analyzing locally.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.