Security audit
Humanizer by JZ
Security checks across malware telemetry and agentic risk
Overview
This is a text-editing skill for rewriting AI-sounding drafts, with no evidence of hidden execution, data theft, persistence, or destructive behavior.
Install only if you are comfortable with a skill that may read and edit draft files when invoked. Use it on specific pasted text or named files, review diffs before accepting edits, and avoid using it where making AI-assisted writing appear human would violate disclosure, authorship, academic, or workplace rules.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.