ClawHub
Back to skill

Security audit

My Liang Tavily Search

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Tavily web-search skill that sends user-directed search requests to Tavily and does not show hidden or destructive behavior.

Use a dedicated Tavily API key and avoid submitting secrets, private internal URLs, regulated data, or sensitive personal information unless Tavily's data handling is acceptable for your use case. Treat returned web content as untrusted reference material.

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
93% confidence
Finding
The skill invokes an external web search API, but the description does not clearly disclose that user queries and selected search parameters are transmitted to Tavily. This creates a privacy and data-handling risk because users may assume searches are local or fail to realize sensitive prompts, domains, or topical filters are being sent to a third party.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.