VCF Log Explorer (MCP)

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:35 PM UTC
• Version:
  1.0.1

Overview

This skill does what it says: it lets an agent query VMware Log Insight, but users should protect the API token and treat returned logs as sensitive.

Install only for agents that are allowed to see your Log Insight data. Use a least-privilege API token, keep it out of source control and logs, rotate it if exposed, and consider enabling proper TLS verification or a trusted CA bundle instead of relying on verify=False. Treat returned log messages as untrusted content.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Intent-Code Divergence

Low

• Confidence: 77% confidence
• Finding: The code returns raw event text and source fields from the external API directly to the AI while claiming it is formatted securely. Log data is untrusted input and may contain prompt-injection content, secrets, control characters, or misleading instructions that can influence downstream agent behavior or expose sensitive information.

Missing User Warnings

Medium

• Confidence: 86% confidence
• Finding: The setup instructions require users to place a sensitive API token into MCP server configuration without warning about secure storage, token scope, logging exposure, or rotation. In agent ecosystems, such credentials can be exposed through config files, process environments, debug output, or downstream tool misuse, increasing the chance of unauthorized access to Log Insight.

VirusTotal

67/67 vendors flagged this skill as clean.