Brand Voice Writer — AI Content in Your Voice
Security checks across malware telemetry and agentic risk
Overview
This instruction-only writing skill reads local brand and trend files to create draft content, with no evidence of hidden execution, credential use, publishing, exfiltration, or destructive behavior.
Install this if you are comfortable giving the agent access to your local brand voice profile, writing examples, and trend reports. Keep secrets, private client data, and sensitive account information out of those files, and review generated drafts before publishing or scheduling them.
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
66/66 vendors flagged this skill as clean.