ClawHub

search1

Security checks across malware telemetry and agentic risk

Overview

This skill does what it advertises: it runs a user-invoked Tavily web search using the user's Tavily API key.

Install only if you are comfortable sending search queries to Tavily under your Tavily API key. Avoid entering secrets or sensitive personal data in search queries, and verify the package metadata if strict provenance matters to you.

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 (2)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill description and usage text do not warn that search queries and related request data are transmitted to the external Tavily API. Users may supply sensitive prompts, identifiers, or investigative terms under the assumption that the action is local, resulting in unintended disclosure to a third party.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
User search queries and the API credential are transmitted to a third-party provider, but the code provides no user-facing disclosure, consent mechanism, or warning about external data handling. In an agent setting, users may supply sensitive prompts or proprietary data, so undisclosed transmission creates a real privacy and compliance risk even if the functionality is intended.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal