ClawHub
Back to skill

Security audit

Tavily Search Pro Native Node

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Tavily web-research helper that sends searches and extraction URLs to Tavily and stores local cache/log files, with controls for sensitive use.

Install only if you are comfortable using Tavily as a third-party research API. Avoid sending client/private or sensitive queries unless approved, and use --no-log --no-cache for sensitive approved work because default logs and cached results may remain in your local OpenClaw cache directory.

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

Low
Confidence
94% confidence
Finding
The skill writes search queries and extracted URL lists to a local usage log, which can expose sensitive research topics, internal targets, or investigation data to other local users, backups, or later compromise of the host. The risk is reduced by the local-only scope and the presence of a --no-log flag, but it remains a privacy/security issue because help text does not clearly warn that this logging occurs by default.

Missing User Warnings

Low
Confidence
91% confidence
Finding
The extract command sends user-supplied URLs to Tavily's external API, which can disclose sensitive internal investigation targets or private URLs to a third party. The code does include useful protection by rejecting localhost/private-network URLs, so this is more of a disclosure/transparency issue than an SSRF issue, but users should be explicitly warned before external transmission.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec, suspicious.env_credential_access

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/self-test.mjs:26

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/tavily-pro.mjs:43