Brand Voice
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only brand voice skill that creates a local style guide and does not show hidden, destructive, or credential-seeking behavior.
Reasonable to install for brand voice and style-guide work. Review the generated `.agents/brand-voice-guide.md` for accuracy, and avoid placing secrets, credentials, or sensitive customer details in it because future content tasks may rely on that file.
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
63/63 vendors flagged this skill as clean.