Wilma

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Wilma school-system reader, but it handles sensitive student data and stored login material.

Install only if you trust @wilm-ai/wilma-cli and want an agent to read Wilma school data. Protect the Wilma config file, avoid sharing or logging TOTP secrets, prefer explicit --student and date filters, and use --all-students only when broad access is intended.

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: 89% confidence
Finding: The skill explicitly documents that local config stores Wilma session credentials for accessing student data and later describes saving and auto-using TOTP secrets, but it does not pair this with clear warnings about credential sensitivity, local file protection, or the risk of exposing secrets to the agent context. In an agent-integrated skill that handles minors' educational records, normalizing persistent session and MFA-secret storage without safeguards materially increases the chance of credential theft, unauthorized account access, and privacy violations.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal