PluginEval Core

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:36 PM UTC
• Version:
  1.0.0

Overview

This skill is a local skill-quality evaluator with read-only default behavior, but it includes an optional write mode users should invoke carefully.

Use it normally for read-only checks with --layer1 or --anti-patterns. Before using --auto-fix --allow-write, run the preview first and apply it only on a version-controlled or disposable copy, because it can modify SKILL.md and remove empty reference files in the target skill directory.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• 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

Findings (2)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 87% confidence
• Finding: The skill advertises no declared permissions, yet its documented usage and the associated analysis indicate read/write capabilities. Undeclared write access is dangerous because users and orchestrators cannot accurately assess what the skill may modify, which breaks least-privilege expectations and can lead to unintended file changes in skill directories.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 95% confidence
• Finding: The documented purpose presents the skill as a self-contained evaluation engine, but the observed behavior includes auto-fixing SKILL.md, creating backups, deleting empty files, and a write-capable mode. This mismatch is dangerous because users may invoke what appears to be a passive analyzer while actually granting a mutating tool the opportunity to alter or delete repository contents.

VirusTotal

57/57 vendors flagged this skill as clean.