ClawHub
Back to skill

Security audit

SmartBill Invoicing

Security checks across malware telemetry and agentic risk

Overview

This is a coherent SmartBill invoicing helper, but it can use real SmartBill credentials and issue real invoices when explicitly approved.

Install only if you trust this publisher with your SmartBill account. Keep the SmartBill token private, run dry-run validation first, approve --allow-final only after checking invoice details, and avoid debug logging unless you are comfortable with invoice/client details appearing in logs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill clearly relies on sensitive capabilities: reading secrets from environment variables, making network calls to the SmartBill API, and reading/writing local files for invoice JSON and downloaded PDFs. Yet the skill declares no explicit permissions, which weakens policy enforcement and user visibility into what the skill can access, increasing the risk of over-privileged execution or unnoticed secret/file exposure.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill documents a live `POST /invoice` operation that can create final invoices, but it does not prominently warn users that this action has real external business and accounting consequences. In an agentic or automated context, that omission increases the risk of unintended issuance of legally or operationally meaningful documents, especially since `isDraft: false` is shown in the example payload.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.