ClawHub
Back to skill

Security audit

Lightfield

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Lightfield connector helper that uses the OOMOL CLI for read-oriented Lightfield data access.

Install this only if you intend to let the agent read Lightfield data through your OOMOL-connected account. Review the OOMOL CLI installer and your Lightfield connection scopes before first use, and treat returned accounts, contacts, opportunities, and custom records as potentially sensitive business data.

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
89% confidence
Finding
The description says to use this skill for ANY Lightfield request and instead of calling the API directly, which is an overly broad invocation trigger. That can cause the agent to route many loosely related requests through this skill automatically, increasing the chance of unintended tool execution and reducing opportunities to apply narrower task-specific safeguards.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.