ClawHub
Back to skill

Security audit

budget-analyzer-claw

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed OpenClaw usage-cost analyzer with local calculation scripts and no evidence of hidden data transfer or destructive behavior.

Before installing, review the billing rates, budget limits, Feishu recipient, and currency assumptions. Treat generated cost reports as sensitive, and require confirmation before broad cross-session reports or any action that would pause agents.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The activation conditions are broad enough to match common budget- or cost-related language, which can cause the skill to trigger outside the user's intended context. In a skill that accesses session-wide usage and billing information, unintended activation can expose sensitive cost data or lead the agent to perform unnecessary data collection and analysis.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal