ClawHub
Back to skill

Security audit

Tavily Search Secure

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Tavily web search and URL extraction helper whose network and API-key use fit its stated purpose.

Install only if you intend to use Tavily and are comfortable sending your search terms or target URLs, along with your Tavily API key, to Tavily's API. Do not use it for confidential queries or private/internal URLs unless that matches your data policy.

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
  • 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 (11)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill invokes scripts that require environment access (TAVILY_API_KEY) and network access, but it does not declare any explicit tool scope such as permissions or allowed-tools. This weakens least-privilege controls and can allow the skill to run with broader capabilities than reviewers or runtime policy expect, increasing the risk of unintended network access or secret exposure through the executed scripts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description and main instructions are written as imperative Turkish-only guidance ('Tavily API ile ... yap', 'çalıştır') with no indication that another language is supported or that Turkish is required for a region-specific purpose. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

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 113)May include surrounding context.

js
let resp;
try {
  resp = await fetch('https://api.tavily.com/extract', {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The script emits Turkish-only messages such as 'Query boş olamaz.' and 'Query çok uzun...', and later also uses Turkish for other failures. This imposes a specific language on users without opt-in or any documented justification, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The message 'topic sadece general veya news olabilir.' and later failure text like 'Tavily isteği başarısız' are user-facing strings fixed to Turkish. The file does not provide any language selection mechanism or documented reason for restricting output to that locale.

Content

No source excerpt is available for this finding.

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 113)May include surrounding context.

js
let resp;
try {
  resp = await fetch('https://api.tavily.com/search', {
    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 92)May include surrounding context.

js
let resp;
try {
  resp = await fetch('https://api.tavily.com/search', {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',

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 92)May include surrounding context.

js
let resp;
try {
  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
94% confidence
Finding

The code sends the user's query, topic, and other request data to https://api.tavily.com/search, which is a network operation that transmits user-provided data off-system. While the network call is inherent to a search tool, this file contains no confirmation prompt, warning message, or explanatory comment/docstring disclosing that external transmission occurs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

This code presents error and status text in both Turkish and English, such as Turkish URL-validation errors and English usage/failure messages. That creates an implicit language policy inconsistency without user opt-in or any documented locale choice, which can violate language/locale expectations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The code reads TAVILY_API_KEY from process.env, which is access to sensitive credentials. This file includes no comment, docstring, or user-facing notice explaining that an API credential is required and will be used for outbound requests.

Content

No source excerpt is available for this finding.