编程规范指南
Security checks across malware telemetry and agentic risk
Overview
This skill is a coding-style guide only and does not add executable behavior, data access, persistence, or privileged actions.
Safe to install from a security perspective. The main consideration is workflow fit: it will bias the agent toward cautious, small, explicitly verified coding changes and may ask for clarification on ambiguous tasks.
SkillSpector
By NVIDIA
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
65/65 vendors flagged this skill as clean.