ClawHub
Back to skill

Security audit

search-specialist

Security checks across malware telemetry and agentic risk

Overview

This is a prompt-only search helper with broad but visible search guidance; users should set privacy and source limits for sensitive research.

Install is reasonable for a search-focused prompt skill. For sensitive, private, legal, medical, financial, or authenticated-source research, tell the agent what sources are allowed, whether APIs or crawlers may be used, and what information must not be shared externally.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill advertises 'deep web access,' 'API utilization,' and 'custom crawlers' without any consent, privacy, authorization, or data-handling warnings. In a search-focused skill, these capabilities materially increase the chance of sending user queries or sensitive context to third parties, accessing restricted resources, or performing retrieval actions beyond user expectations.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.