ClawHub
Back to skill

Security audit

Exa Web Search (Free)

Security checks for vulnerabilities and agentic risk

Overview

The skill is a clear Exa search integration, but it asks users to persistently enable broad third-party research tools without enough privacy or scoping guidance.

Review before installing. Use the core Exa MCP tools only for information you are allowed to send to Exa, and avoid secrets, proprietary source code, personal data, or sensitive business research unless your policy permits it. Prefer enabling only the specific tools you need instead of the all-tools configuration, especially for crawling, people search, and deep researcher features.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to connect to and use an external Exa MCP service for web, code, and company research, but it does not clearly disclose that user queries and any embedded sensitive content will be transmitted to a third-party service. This creates a data privacy and compliance risk because users may submit confidential prompts, internal code, or business intelligence without informed consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The advanced tool section enables crawling and people/profile search capabilities without any warning about privacy, consent, or data handling implications. These features materially increase the chance of collecting, enriching, or transmitting personal or sensitive data to a third-party service in ways users may not anticipate.

Content

No source excerpt is available for this finding.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
84% confidence
Finding

The skill recommends an 'Enable all tools' configuration that activates broad capabilities, including crawling, people search, and agentic research, without applying least-privilege principles. This increases exposure by making higher-risk tools available by default, which can lead to unnecessary data access, broader external transmission, and misuse beyond the user's immediate task.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

  • people_search_exa - Professional profiles
  • deep_researcher_start/check - AI research agent

Enable all tools:

bash
mcporter config add exa-full "https://mcp.exa.ai/mcp?tools=web_search_exa,web_search_advanced_exa,get_code_context_exa,deep_search_exa,crawling_exa,company_research_exa,people_search_exa,deep_researcher_start,deep_researcher_check"

Static analysis

No suspicious patterns detected.