ClawHub
Back to skill

Security audit

omnisearch

Security checks across malware telemetry and agentic risk

Overview

This is a coherent web-search skill whose network use is expected, with no artifact evidence of hidden persistence, credential theft, destructive actions, or unrelated data transfer.

Install only if you are comfortable with your search queries being sent to the configured search provider. Avoid including secrets, private customer data, or sensitive local context in searches unless you intend to disclose it to that provider.

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 explicitly instructs the agent to run searches immediately and not ask permission, even though user queries are sent to external providers such as Perplexity, Brave, Kagi, Tavily, or Exa. This creates a privacy and consent risk because sensitive user input may be transmitted off-platform without notice, and the 'mandatory' framing increases the likelihood of over-sharing context that should first be minimized or confirmed.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.