ClawHub
Back to skill

Security audit

Wilma

Security checks across malware telemetry and agentic risk

Overview

The skill appears purpose-built for Wilma access, but it handles sensitive student records and account secrets with insufficient safety guidance.

Install only for Wilma accounts you are authorized to access. Treat the local Wilma config and any TOTP secret as credentials, avoid passing secrets on the command line when possible, and review AI-generated summaries before sharing because they may contain private student information.

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
95% confidence
Finding
This markdown file describes that the skill uses a local config containing Wilma session credentials and can access grades, attendance notes, messages, and other student data. Under the markdown criteria for missing user warnings, the description should explicitly warn users about privacy-sensitive educational data and credential handling, but it presents these capabilities as routine usage without a clear caution.

Missing User Warnings

High
Confidence
98% confidence
Finding
The markdown explicitly tells users to save a TOTP secret for automatic login and shows passing the secret on the command line. This affects account security because command-line secrets may be exposed via shell history, process listings, or logs, yet the documentation provides no warning or safer handling guidance.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.