ClawHub
Back to skill

Security audit

LeadsDaddy B2B Lead Finder

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed LeadsDaddy B2B lead-finding skill with expected third-party setup and credit-use considerations.

Before installing, verify the @leadsdaddy/mcp npm package and LeadsDaddy URLs, use a scoped LeadsDaddy token, and require explicit approval before any lead_unlock action that may spend credits or reveal contact 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 invocation description is broad enough to trigger on many generic sales, market research, or prospecting requests, which can cause the agent to select this skill in contexts where the user did not explicitly ask to use LeadsDaddy or perform external lead discovery. Because the skill can create tasks, profile products, and unlock leads against a third-party service, over-selection increases the chance of unnecessary external data processing, unintended spend, and actions taken on loosely specified user intent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.