Back to skill

Security audit

Minimax Tavily Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Tavily web search and URL extraction helper that sends user-supplied queries or URLs to Tavily using the user's API key.

Install only if you are comfortable sending search queries, requested URLs, and your Tavily API key to Tavily's API. Do not use the extraction command on private, sensitive, or access-controlled URLs unless that third-party processing is acceptable.

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
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
91% confidence
Finding

The skill advertises and relies on sensitive capabilities (env for TAVILY_API_KEY and outbound network access to Tavily) but does not declare an explicit tool scope such as permissions or allowed-tools. This creates a least-privilege and transparency problem: a host agent may grant broader access than intended, and reviewers/users cannot easily verify the exact operational boundaries of the skill.

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
97% confidence
Finding

The implementation calls Tavily's /extract endpoint and submits arbitrary URLs for raw content extraction, which materially exceeds the stated skill purpose of concise web search result retrieval. This capability mismatch is dangerous because it enables full-page content acquisition through a third party, increasing data exposure and creating a misleading trust boundary for users and agents that expect only search behavior.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The script outputs raw contents for any supplied URL, giving the skill arbitrary web content extraction capability unrelated to a minimal web-search function. In agent settings, this is dangerous because it can be abused to collect and relay sensitive or policy-restricted page contents via the Tavily service and then print them downstream without meaningful restriction.

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",

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This code sends user-provided query data and the TAVILY_API_KEY to api.tavily.com via an HTTP POST request. While the network call is visible in code, there is no confirmation prompt, user-facing disclosure about external transmission, or inline warning explaining that input and credentials will be sent to a third-party service.

Content

No source excerpt is available for this finding.