ClawHub
Back to skill

Security audit

Tavily AI Search

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Tavily web-search helper, with normal third-party search and API-key privacy considerations but no hidden or destructive behavior found.

Install this only if you are comfortable sending search queries and selected options to Tavily under your API key. Avoid using it with secrets, private internal documents, regulated data, or sensitive personal information, and treat search results or URLs fetched with curl as untrusted content. Pin or review the tavily-python dependency in stricter environments.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill documents use of an API key via environment variable/config but do not declare corresponding permissions or clearly scope that capability. This can bypass least-privilege expectations and make secret access less visible to operators reviewing what the skill can read or transmit.

Vague Triggers

Medium
Confidence
79% confidence
Finding
The description is broad enough to trigger on many generic research or fact-finding prompts, which increases the chance the agent sends user queries to this third-party search service unnecessarily. Over-broad routing can cause avoidable data disclosure and unexpected external calls, especially for sensitive or internal research requests.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill lacks a prominent warning that user queries and potentially retrieved page content are sent to Tavily and may involve further third-party content processing. Without this disclosure, users and operators may unknowingly expose sensitive prompts, URLs, or extracted content to an external service.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.