ClawHub
Back to skill

Security audit

Tavily Search 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Tavily web search and URL extraction wrapper with disclosed API key and network use, and I found no hidden persistence, privilege escalation, or unrelated behavior.

Install only if you are comfortable sending search queries and any extracted URLs to Tavily under your Tavily account. Do not use the extract command on confidential, internal, localhost, or otherwise sensitive URLs unless that disclosure is acceptable.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill invokes Node.js scripts that require an API key and perform outbound web requests, but the manifest does not declare any explicit tool scope such as permissions or allowed-tools. This creates a trust and containment gap: an agent or platform may expose environment variables and network access more broadly than intended, making it harder to enforce least privilege or review the skill’s runtime capabilities.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The script accepts arbitrary user-provided URLs and submits them for extraction, which exceeds the narrower 'AI-optimized web search' purpose described in the skill metadata. In an agent setting, this capability expansion can be abused to exfiltrate content from sensitive or internal URLs that an agent is induced to pass along.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/extract.mjs (reported line 24)May include surrounding context.

js
process.exit(1);
}

const resp = await fetch("https://api.tavily.com/extract", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/extract.mjs (reported line 24)May include surrounding context.

js
process.exit(1);
}

const resp = await fetch("https://api.tavily.com/extract", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/search.mjs (reported line 62)May include surrounding context.

js
process.exit(1);
}

const resp = await fetch("https://api.tavily.com/extract", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill metadata says it provides web search, but this script calls Tavily's extract endpoint to retrieve raw content from arbitrary supplied URLs. That is a materially broader capability than search and can expose full page contents to the remote API and downstream consumers, increasing data-handling and policy risk through misleading documentation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The script transmits both user-supplied URLs and the API key to an external service without any user-facing disclosure or confirmation. In a security-sensitive agent environment, silent third-party transmission of requested targets can leak sensitive browsing targets, document locations, or internal resources the agent was asked to inspect.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/search.mjs (reported line 62)May include surrounding context.

js
body.days = days;
}

const resp = await fetch("https://api.tavily.com/search", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",

Static analysis

No suspicious patterns detected.