Security audit

Tavily OpenClaw plugin

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Tavily web search and extraction plugin whose network use is purpose-aligned, though users should avoid sending sensitive queries or private URLs to Tavily.

Before installing, understand that search queries and URLs submitted for extraction go to Tavily or any configured base URL. Do not include secrets, tokens, private internal links, or sensitive personal data unless you have approved that disclosure.

SkillSpector

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 (1)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill documentation does not warn users that search queries and submitted URLs are transmitted to the external Tavily service. This can cause users or downstream agents to send sensitive prompts, internal URLs, tokens, or private research targets to a third party without informed consent, creating a data disclosure and privacy risk.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.