Skill Refactor

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only skill for evaluating and rewriting other skills, with no code, install commands, credential use, or hidden access.

Install this if you want a Chinese-language framework for skill review and refactoring. Review any recommendation to delete, merge, or rewrite a skill before applying it, especially when the skill activates from broad terms like skill optimization or skill evaluation.

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: 92% confidence
Finding: The trigger list is very broad and includes multiple generic phrases such as '技能优化' and '技能评估', which can cause the skill to activate outside its intended context. In an agent system, unintended invocation can redirect user requests into a destructive 'eliminate/refactor' workflow, potentially altering or deleting skills when the user did not explicitly request that behavior.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal