ClawHub
Back to skill

Security audit

LeadBoxer

Security checks across malware telemetry and agentic risk

Overview

This skill is a narrow LeadBoxer lookup helper that uses the OOMOL CLI for disclosed read-only domain and IP enrichment actions.

Install this only if you intend to let Codex perform LeadBoxer domain or IP enrichment through your OOMOL-connected account. Be aware that lookup inputs will be sent through the OOMOL LeadBoxer connector, and avoid using it for ambiguous mentions of LeadBoxer unless you actually want an external lookup.

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
90% confidence
Finding
The instruction to use this skill for ANY LeadBoxer request and instead of calling the API directly is overly broad and can cause the agent to invoke the skill for loosely related mentions without validating user intent. In practice, this can expand the skill’s execution scope, increase unnecessary access to connected third-party data, and make accidental data exposure or unintended external calls more likely.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.