Human Writing
Security checks across malware telemetry and agentic risk
Overview
This is a text-only writing and editing skill with no suspicious access, persistence, or hidden behavior found.
This skill appears safe to install for writing review and rewrite tasks. As with any writing assistant, review generated copy for factual accuracy, tone, and whether it preserves your intended voice before publishing.
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.