Security audit
Verified Humanizer New
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed local writing helper with privacy guardrails and no evidence of hidden data access or unsafe behavior.
Reasonable to install for local text rewriting and evaluation. Before relying on provenance, check the package identity/version mismatch, and when using optional verification, send only metrics rather than original or rewritten private 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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.