LYGO Guardian P0 Stack

• Outcome: Pass
• Latest audit: May 28, 2026 at 10:48 AM UTC
• Version:
  0.1.0

Overview

This is a local Python moderation wrapper; its docs overstate some logging and integration ideas, but the shipped code does not show hidden access, network use, persistence, or destructive behavior.

Install this only if you want a simple local moderation helper. Treat it as a lightweight heuristic wrapper, not a complete safety system, audit logger, or replacement for platform safeguards and human review around public posting, tool calls, financial actions, or memory writes.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 90% confidence
• Finding: The skill advertises and documents code usage that can execute Python and references external URLs, while the manifest shown in SKILL.md does not declare any permissions. This creates a capability transparency problem: users or hosting platforms may assume the skill is passive/documentation-only, but it appears designed to operate with code execution and likely network-relevant behavior, increasing the risk of unintended outbound access or unsafe integration decisions.

VirusTotal

55/55 vendors flagged this skill as clean.