Modified Code Review

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:14 PM UTC
• Version:
  1.0.1

Overview

This is a simple code-review guidance skill with no scripts, install hooks, persistence, or hidden data handling in the inspected artifacts.

Install this if you want a Chinese-oriented structured code-review helper. Invoke it explicitly for diffs, PRs, or changed files, and be aware it may otherwise trigger on broad requests for best practices or code scoring.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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 (2)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The activation text is broad enough to match generic requests such as code review, best practices, or scoring, which can cause the skill to trigger outside its narrowly intended use. Over-broad routing can expose users to unintended behavior, reduce predictability, and let this skill intercept requests better handled by other, more specific skills.

Natural-Language Policy Violations

Medium

• Confidence: 83% confidence
• Finding: The README indicates a fixed Chinese output format without stating that the user's language should be respected or that there is a justified locale constraint. This can cause misleading or unusable responses for users in other languages, increasing the chance that they misunderstand review results or miss important security recommendations.

VirusTotal

64/64 vendors flagged this skill as clean.