ClawHub
Back to skill

Security audit

LightSpeed VT

Security checks across malware telemetry and agentic risk

Overview

This LightSpeed VT skill is a disclosed, read-only connector wrapper with minor guidance needed around broad invocation wording and CLI setup.

Install only if you intend your agent to retrieve LightSpeed VT courses, locations, or users through your connected OOMOL account. Treat user-listing results as potentially sensitive, and review any oo CLI install or login step before allowing it.

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
92% confidence
Finding
The description says to use this skill for "ANY LightSpeed VT request," which is an overly broad trigger that can cause the agent to invoke the skill for loosely related prompts without sufficient user intent verification. In a connector-backed skill, this increases the chance of unnecessary access to third-party data and can bypass more precise tool-selection safeguards, even though the listed actions are read-only in this version.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.