ClawHub
Back to skill

Security audit

Better Tavily Search

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Tavily web-search helper that sends user-directed searches and URLs to Tavily using a disclosed API key.

Install only if you are comfortable sending search terms, URLs, extraction targets, and mapping targets to Tavily or a Tavily-compatible endpoint configured by your environment. Use a limited Tavily API key, keep ~/.openclaw/.env private, and avoid putting secrets, internal URLs, or confidential research terms into searches unless that disclosure is acceptable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill explicitly describes capabilities to read environment variables and `~/.openclaw/.env`, invoke a Python script, and perform external web requests, yet it declares no permissions. This creates a trust and enforcement gap: a caller may treat the skill as low-privilege while it can access secrets and the network, increasing the risk of unintended secret exposure or unreviewed outbound data flows.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.