Human Writing
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only writing-style skill with no code, credentials, or install steps, but it should be used transparently because it is designed to make AI-written text sound more human.
This skill appears safe to install as a writing-style aid. Use it to improve documentation clarity, but do not use its AI-tell removal guidance to misrepresent authorship in settings that require AI disclosure.
VirusTotal
66/66 vendors flagged this skill as clean.
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.
Generated documentation may read as if written by a human, which is fine for polish but could mislead readers if AI assistance must be disclosed.
The skill openly instructs the agent to make generated text sound less like AI output. That is purpose-aligned for style editing, but users should avoid using it to conceal AI authorship where disclosure is expected.
designed to purge common LLM stylistic "tells" and replace them with the precision of a senior engineer or domain expert
Use the skill for clarity and professional tone, but disclose AI assistance when required by policy, publication rules, school rules, or workplace expectations.
If an environment supplies a separate SOUL.md file, chat tone could be influenced by instructions not reviewed in this package.
The artifact references a SOUL.md persona source that is not included in the provided file manifest. This is a minor provenance gap for style/personality guidance, not code execution or credential use.
Casual Chat (with User): Follow the SOUL.md personality (Sassy, Devoted).
Include the referenced persona file in the skill package or remove the reference so users can review all applicable guidance.