ClawHub
Back to skill

Security audit

Exa Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Exa web-search wrapper that discloses its API-key and network requirements.

Install this only if you are comfortable providing an Exa API key and sending search queries, filters, and optional content requests to Exa. Prefer setting the key in a controlled environment rather than broadly exposing it, and invoke the skill only when you specifically want Exa-backed search.

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 (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill invokes a local Node script that uses both environment secrets (EXA_API_KEY) and outbound network access, but the manifest does not declare any explicit tool scope such as permissions or allowed-tools. This creates a least-privilege gap: reviewers and enforcement layers cannot clearly constrain or validate what capabilities the skill is expected to use, increasing the risk of unintended secret exposure or broader networked behavior if the script changes or is abused.

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/exa_search.mjs (reported line 102)May include surrounding context.

js
body.endPublishedDate = endDate ?? undefined;
  }

  const res = await fetch("https://api.exa.ai/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/exa_search.mjs (reported line 102)May include surrounding context.

js
body.endPublishedDate = endDate ?? undefined;
  }

  const res = await fetch("https://api.exa.ai/search", {
    method: "POST",
    headers: {
      "content-type": "application/json",

Static analysis

No suspicious patterns detected.