ClawHub
Back to skill

Security audit

Icp Qualifier

Security checks across malware telemetry and agentic risk

Overview

This is a plain instruction-only sales lead scoring skill with no code or requested tools, but users should apply its demographic and geography filters carefully.

Install only if you want a manual prospecting rubric for DTC ecommerce leads. Treat the US-only, gender, and age criteria as business-risk filters that need human review, verify public contact details before outreach, and comply with applicable privacy, platform, and anti-spam requirements.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The skill's ICP definition explicitly restricts targets to 'Based in United States only,' which is a natural-language locale policy constraint. The file does not present this as an optional filter chosen by the user or justify it as a documented region-specific compliance requirement.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The scoring system awards points specifically for 'Location (US only),' embedding a fixed locale preference into the qualification logic. This forces a geographic policy choice rather than offering the user control over target market selection.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.