Back to skill

Security audit

plugin-review

Security checks across malware telemetry and agentic risk

Overview

This skill is a plugin quality review guide with local review commands that fit its stated purpose, though its activation triggers are broad.

Install this if you want a structured plugin review workflow. Be aware that its generic triggers may activate during unrelated review or quality discussions, and review the local commands before running branch, PR, or release checks in a repository.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
97% confidence
Finding
The listed triggers include generic terms like "review," "quality," "validation," "testing," and "architecture," which are common words that can appear in many unrelated user requests. The file does not provide narrowing context, explicit activation constraints, or negative examples to distinguish when this skill should or should not activate.

Missing User Warnings

Low
Confidence
91% confidence
Finding
This markdown file directs the user to run local Python scripts and a shell pipeline (`meta_evaluation.py`, `generate_dependency_map.py`, and `diff`) but does not include any warning about executing commands on the local system. Because markdown files should disclose behaviors that could affect system integrity, the absence of any caution or note is a quality/safety gap.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
70% confidence
Finding
Shadow Command Trigger: 'review' conflicts with built-in command 'review'

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.