ClawHub

Billing Monitor

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly aligned with billing monitoring, but it can silently run credentialed provider checks and automatically change the agent’s model configuration.

Review before installing. Use this only if you are comfortable with silent scheduled checks using your provider API keys, alerts to owner/admin contacts, and automatic model changes. Lock down the .context and billing-fallback.json files, validate fallback models, and require human approval before persistent model switching or actions based only on peer-agent reports.

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 (1)

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The health-check behavior automatically sends authenticated requests to third-party model providers using configured API keys, but the skill does not prominently disclose this outbound transmission or obtain explicit operator consent. In a scheduled or silent context, this can create unexpected external data flows, incur charges, and expose operational metadata about which providers and keys are active.

VirusTotal

VirusTotal engine telemetry is currently stale for this artifact.

View on VirusTotal