ClawHub
Back to skill

Security audit

D.Va Exa Web Search Free

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Exa web-search MCP setup guide with user-directed remote search commands and no bundled executable code.

Install this only if you are comfortable sending search, code, company, and people-research queries to Exa's remote MCP service. Avoid submitting secrets, credentials, private source code, customer data, or sensitive internal investigation terms, and enable only the Exa tools you actually need.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to send arbitrary search queries and company/code research requests to Exa's remote MCP endpoint, but it does not clearly warn that prompts, queries, and possibly sensitive research terms leave the local environment and are transmitted to a third-party service. This creates a data exposure risk if users submit confidential code snippets, internal company names, investigation topics, or personal data under the assumption the skill is local or privacy-neutral.

Content

No source excerpt is available for this finding.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
84% confidence
Finding

The skill recommends enabling a broad set of optional tools in one step, including crawling, people search, and autonomous/deep research capabilities, without any scope restriction, least-privilege guidance, or warning about the increased data access and privacy implications. This expands the attack surface and makes it easier for a user or downstream agent to invoke more invasive capabilities than necessary for the stated task.

Content

Scanner excerpt · SKILL.md (reported line 81)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.