中文内容精修助手
ReviewAudited by ClawScan on May 12, 2026.
Overview
Prompt-injection indicators were detected in the submitted artifacts (unicode-control-chars); human review is required before treating this skill as clean.
This skill appears safe to install as an instruction-only text rewriting helper. Before using it, decide whether making AI-generated text look human is appropriate for your context, and do not let it read or edit files unless you intentionally provide those files and review the result. ClawScan detected prompt-injection indicators (unicode-control-chars), so this skill requires review even though the model response was benign.
Findings (2)
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.
Outputs may make AI-written content appear more human-written to readers on social or publishing platforms.
The skill openly advertises making AI-generated text less recognizable as AI-written. That is purpose-aligned and disclosed, but it can affect how readers perceive authorship.
AI 写的中文一眼就能看穿？这个技能帮你藏好 AI 尾巴。
Use the skill only where this is acceptable, and follow any disclosure, academic, workplace, or platform rules about AI-generated content.
If used on files, the agent could read or modify local documents rather than only returning rewritten text in chat.
The skill declares local file read/write/edit tools, while its documented workflow mainly says users provide text and the agent returns polished text. This is not inherently unsafe, but file mutation should be clearly user-directed.
allowed-tools: - Read - Write - Edit - AskUserQuestion
Only allow the skill to read or edit files you explicitly select, and review changes before saving or sharing them.