Security audit
Writing Style Zhengliu
Security checks across malware telemetry and agentic risk
Overview
This is a writing-style skill that restructures long text and optionally generates local infographic outputs, with no evidence of hidden execution, credential access, exfiltration, or destructive behavior.
Install if you want an aggressive structured rewriting style for distilling long text. Be aware it applies broadly and may create local infographic files; avoid using sensitive documents unless you trust the surrounding helper tools and local output handling.
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.
Static analysis
No suspicious patterns detected.