ClawHub
Back to skill

Security audit

Exa Web Search Nodeskai

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Exa MCP search helper with optional advanced research tools, but users should enable only the tools they actually need.

Install only if you are comfortable sending search queries, company names, profile searches, and crawled URLs to Exa. Prefer the default exa configuration for normal search, and enable exa-full only when you specifically need crawling, people search, or 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill advertises optional people_search_exa and crawling_exa capabilities without any privacy, consent, or data-sensitivity guidance. In a search/research skill, these features can be used to collect personal profile data or extract full page contents from sites that may contain sensitive information, increasing the risk of misuse or overcollection.

Content

No source excerpt is available for this finding.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
87% confidence
Finding

The skill provides a one-step configuration to enable all advanced tools, including people search, crawling, and autonomous deep research, without recommending least-privilege configuration or warning about the expanded risk surface. This makes it easy for users or downstream agents to activate unnecessary high-risk capabilities that could facilitate excessive data collection or unintended actions.

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"