代码审查专家

Security checks across malware telemetry and agentic risk

Overview

This is a simple Python code review checklist skill with no commands, credentials, network use, or persistence.

This skill is appropriate for normal Python code review. Users should avoid pasting secrets or private credentials into code they submit for review, and should remember that it is a checklist-based reviewer rather than a full security audit tool.

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 (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill description is broad enough to match many generic requests for code review or feedback, which can cause over-invocation without clear scope boundaries. This is dangerous because it may route sensitive, unsupported, or non-Python review requests to a skill that presents itself as authoritative, increasing the chance of misleading analysis or inappropriate handling of user data.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal