Security audit
Brand Language Codifier
Security checks across malware telemetry and agentic risk
Overview
This markdown-only skill provides brand voice and naming guidance, with no executable code or hidden install behavior found.
Install this if you want an agent to help codify brand voice and naming rules. Before using it, be aware that approved saves may write brand-language outputs and claim candidates into local memory files, and any public-page scraping should be limited to your own brand materials.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.