Mcp Skill

Security checks across malware telemetry and agentic risk

Overview

This is a small documentation-only wrapper for an external Exa MCP research service, with no evidence of hidden code, persistence, or malicious instructions.

Install this only for research tasks where you are comfortable sending prompts and lookup inputs to the Exa MCP service. Avoid submitting secrets, credentials, private code, regulated data, or confidential business material unless you trust that provider’s data handling.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill advertises web search, crawling, code-context retrieval, and research features backed by an external MCP endpoint, but it does not disclose that user prompts, search terms, URLs, or retrieved context may be transmitted to a third-party service. This creates a real data-exposure risk because users or downstream agents may supply sensitive internal queries or documents under the assumption the skill is local or self-contained.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal