ClawHub
Back to skill

Security audit

TalentLMS

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed TalentLMS connector skill that can read and manage TalentLMS users through the OOMOL oo CLI, with explicit confirmation required for write and delete actions.

Install only if you intend to let an agent operate your TalentLMS account through OOMOL. Review every proposed create, update, or delete payload before approval, especially delete_user, and make sure your OOMOL TalentLMS connection has only the access your workflow needs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill description instructs the agent to use this skill for ANY TalentLMS request, which is an overly broad trigger that can cause the skill to be invoked for all TalentLMS-related tasks without additional narrowing. In a skill that includes write and destructive actions such as user creation, update, and deletion, broad routing increases the chance of unintended use, inappropriate action selection, or bypass of more specific safeguards in alternative workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.