humanize-zh-writing
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is an instruction-only Chinese writing helper with no code, install steps, credentials, or system access; the main thing to notice is that it is designed to make AI-written text seem more human.
This skill appears safe from a technical security perspective because it is only a prompt/instruction file. Before installing, consider whether your use case allows AI-assisted rewriting or requires disclosure, and avoid using it to hide AI involvement in academic, professional, legal, or journalistic contexts where authorship transparency matters.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Readers may believe rewritten text was authored naturally by a person unless the user discloses AI assistance where appropriate.
The skill openly aims to make text read as if written by a human. This is central to the stated purpose and not hidden, but it could be used to obscure AI assistance from readers.
去掉 AI 痕迹；模拟该文体真人写作特有的不完美
Use for style improvement, but do not use it to misrepresent authorship, bypass disclosure rules, or fabricate human experiences; verify factual claims before publishing.