Brand Voice Guide
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only brand voice skill that gives writing guidance and templates without code execution, credentials, persistence, or hidden external actions.
Appropriate to install for brand voice work. Be selective with the examples you provide, especially unreleased positioning, customer support conversations, customer personal data, or confidential launch copy, because the skill relies on user-supplied samples to produce useful guidance.
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
62/62 vendors flagged this skill as clean.