Humanizer
Security checks across malware telemetry and agentic risk
Overview
The skill's requirements and instructions align with its stated purpose (rewriting text to remove AI hallmarks and add human voice); it is instruction-only, requests no credentials, and does not perform suspicious I/O or installs.
This skill is internally consistent and doesn't request credentials or install code, but it explicitly encourages injecting opinion, first‑person voice, and personality when editing. Before using it on important documents: 1) test on non-sensitive sample text to verify the tone changes are acceptable; 2) review outputs for factual accuracy and for any invented assertions or inappropriate personal claims; 3) avoid submitting sensitive or confidential content (the skill will rewrite anything you give it); and 4) if you don't want automated rewriting, ensure your agent's autonomous skill invocation settings require your confirmation before calling the skill.
SkillSpector
SkillSpector findings are pending for this release.
VirusTotal
No VirusTotal findings