Axis Lms

Security checks across malware telemetry and agentic risk

Overview

This Axis LMS skill is coherent, but it gives an agent broad authenticated ability to change LMS data without clear guardrails for risky requests.

Review before installing if your Axis LMS account contains real user, compliance, course, file, report, or transaction data. Use a least-privileged LMS account, prefer discovered Membrane actions, require explicit user confirmation before POST, PUT, PATCH, or DELETE requests, and revoke the Membrane connection when finished.

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: 92% confidence
Finding: The skill explicitly documents a generic proxy mechanism that supports mutating methods like POST, PUT, PATCH, and DELETE without any guardrails, confirmation guidance, or warnings about destructive effects. In an agent setting, this increases the chance that the model issues unsafe direct API calls that modify or delete LMS data, especially when prebuilt actions do not cover the use case.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal