ClawHub
Back to skill

Security audit

Web Search

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward web-search helper that sends search queries to Exa and shows no hidden persistence, credential access, or unrelated local activity.

Install this only if you are comfortable with search terms being sent to Exa's hosted service. Avoid putting secrets, private customer data, confidential internal project names, or other sensitive information in search queries.

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 (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill explicitly directs the agent to run a network-capable command (node ./search.mjs) and its metadata indicates an Exa-hosted transport, but it does not declare an explicit tool scope such as permissions or allowed-tools. That increases the risk of unintended or overbroad network use because users and the runtime lack a clear, enforceable statement of what external access the skill requires.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill says it can search the public web through Exa's hosted MCP endpoint without an API key, but the user-facing description does not clearly warn that search queries and returned context are transmitted to a third-party hosted service. This can lead users to unknowingly send sensitive prompts, internal project names, or other confidential context to an external provider.

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 · search.mjs (reported line 55)May include surrounding context.

js
},
}

const res = await fetch("https://mcp.exa.ai/mcp", {
  method: "POST",
  headers: {
    accept: "application/json, text/event-stream",

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code sends the user-provided query to https://mcp.exa.ai/mcp via an HTTP POST, which transmits user-supplied data to a third-party service. While the network call is central to the tool's purpose, there is no visible warning, print/log statement, comment, or prompt in this file disclosing that the query will be sent externally.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.