业务模块工程师 服务层与业务逻辑

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only coding helper for service-layer refactoring, with no scripts, credential access, persistence, or hidden execution behavior.

Install this if you want an internal coding assistant for service-layer refactoring and business logic placement. Confirm the referenced Weline documents and the `@Weline-技术主管` collaboration convention make sense for your workspace, and review any code changes and test evidence as you normally would.

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
88% confidence
Finding
The invocation guidance is broad enough to match common architectural or coding discussions, which can cause the agent framework to select this skill outside its intended boundary. In an agentic system, over-broad routing increases the chance of inappropriate authority, irrelevant file access, or unintended workflow influence, even though the content itself is not overtly malicious.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal