Back to skill

Security audit

Tavily Clone

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Tavily web-search wrapper that sends search queries to Tavily using a user-provided API key, with no evidence of hidden persistence or unrelated access.

Install only if you are comfortable sending your search queries to Tavily and providing a Tavily API key via TAVILY_API_KEY. Do not use it for sensitive or confidential queries unless Tavily's handling of that data is acceptable for your use case.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Lp1

High
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The script performs an outbound network request to api.tavily.com, but that network capability is not covered by declared permissions. In a skill context, undeclared egress is a security issue because it can transmit user input or secrets to external services without transparent consent or enforcement.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The script performs an outbound network request to api.tavily.com, but that network capability is not covered by declared permissions. In a skill context, undeclared egress is a security issue because it can transmit user input or secrets to external services without transparent consent or enforcement.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

This code transmits user-controlled input and an authentication secret to an external service over the network. The transmission is over HTTPS and aligns with the skill’s purpose, so it is not inherently malicious, but it is still security-relevant because it exposes data to a third party and increases dependency on external handling of that data.

Content

Scanner excerpt · scripts/search.mjs (reported line 11)May include surrounding context.

js
const query = process.argv[2] ?? "test";

const resp = await fetch("https://api.tavily.com/search", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ api_key: apiKey, query, max_results: 5, include_answer: true }),

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

This code transmits user-controlled input and an authentication secret to an external service over the network. The transmission is over HTTPS and aligns with the skill’s purpose, so it is not inherently malicious, but it is still security-relevant because it exposes data to a third party and increases dependency on external handling of that data.

Content

Scanner excerpt · scripts/search.mjs (reported line 11)May include surrounding context.

js
const query = process.argv[2] ?? "test";

const resp = await fetch("https://api.tavily.com/search", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ api_key: apiKey, query, max_results: 5, include_answer: true }),

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The script sends both the user-supplied query and the API key to a third-party service without any user-facing disclosure in the script. Even if expected for functionality, this creates a transparency and privacy risk because users may not realize their input is leaving the local environment and being processed externally.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.