Human Writing
Security checks across malware telemetry and agentic risk
Overview
This is a text-only writing style aid with no code execution or data access, though users should follow any AI-use disclosure rules that apply to their work.
Safe to install from a technical security perspective. Use it as an editing aid, but do not use it to evade rules requiring AI-use disclosure or honest authorship labeling.
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.