ClawHub
Back to skill

Security audit

LLM Cost Guard

Security checks across malware telemetry and agentic risk

Overview

This appears to be a local LLM cost logger, but it overpromises budget blocking and describes unclear scheduled reporting, so users should review it before installing.

Install only if you are comfortable treating this as a local usage logger, not a reliable spending guard. Before using it for budgets, verify whether any OpenClaw cron job is created, what reports it sends and where, how to remove it, and whether enforcement is implemented in your actual LLM request path.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The README states that the skill auto-installs a daily cron job and sends scheduled reports/alerts, which implies persistent system modification and automated outbound actions. Describing this behavior without a prominent opt-in warning or explicit consent requirement is dangerous because users may install the skill expecting passive local tracking, not background task creation that continues running and sending messages after setup.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill explicitly states it auto-installs a daily cron job, which modifies the user's scheduled tasks and creates persistent behavior on the host. Even though the described action is related to reporting and resets, persistence without an explicit opt-in warning can surprise users, create unintended task execution, and be abused if the command or environment is later altered.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal