Security audit
Verified Humanizer 0.0.8
Security checks across malware telemetry and agentic risk
Overview
This skill appears to be a local writing-rewrite helper with no evidence of hidden data transfer or destructive behavior.
This is reasonable to install if you want a local text-polishing workflow. Be aware that it includes an OpenClaw hook that adds a session reminder, and optional verification should only use structured metrics, not the raw text.
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
58/58 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.