ClawHub
Back to skill

Security audit

Tavily Search Pro

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Tavily search integration, with the main consideration that queries and URLs are sent to Tavily.

Install this only if you are comfortable using a Tavily API key and sending selected searches, URLs, crawl targets, and research prompts to Tavily. Use a revocable API key, consider an isolated Python environment, and avoid confidential, private, regulated, or internal-only material unless your organization has approved that disclosure.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill explicitly requires an API key and performs web search, extraction, crawling, mapping, and research against an external service, yet only declares `allowed-tools: [exec]` and does not clearly declare the underlying env and network capabilities. This creates a transparency and policy-enforcement gap: users or hosting systems may underestimate the skill's ability to access secrets and transmit data off-platform.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill documentation describes extract, crawl, map, and research features but does not warn that user-supplied URLs, queries, and potentially fetched page content are sent to Tavily's external service. In this context, the omission is significant because these operations can process sensitive internal URLs, private documents, or proprietary research topics, leading to unintended third-party disclosure.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
This skill sends user-provided search queries, research prompts, URLs, crawl targets, and optional instructions to the external Tavily API, but the CLI does not provide an explicit user-facing disclosure at the point of use that this data leaves the local environment. In an agent-skill context, users may reasonably assume inputs are processed locally, so sensitive prompts, internal URLs, or proprietary research topics could be unintentionally disclosed to a third party.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.