ClawHub
Back to skill

Security audit

Irene Tavily Search

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Tavily web-search helper that sends user-provided searches to Tavily using a configured Tavily API key.

Install only if you are comfortable sending search terms to Tavily. Use a dedicated Tavily API key, keep .env files private, monitor quota usage, and avoid submitting confidential or regulated search terms unless Tavily handling is acceptable for your environment.

SkillSpector

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
86% confidence
Finding
The script sends user queries and the Tavily API key to an external third-party service without any explicit runtime notice, confirmation, or privacy guardrails. In an agent-skill context, users may assume local processing, so sensitive prompts or internal research terms could be unintentionally disclosed to an outside provider.

Static analysis

No suspicious patterns detected.