Remove AI Writing Signs
ReviewAudited by ClawScan on May 14, 2026.
Overview
Prompt-injection indicators were detected in the submitted artifacts (ignore-previous-instructions); human review is required before treating this skill as clean.
This skill appears safe to install from a security perspective because it is instruction-only and does not request code execution, credentials, or system access. Before using it, be clear about how much rewriting you want and avoid using it to misrepresent AI-generated work where disclosure rules apply. ClawScan detected prompt-injection indicators (ignore-previous-instructions), 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.
A user asking for simple cleanup might receive a more aggressive rewrite aimed at removing AI-writing signs.
The skill tells the agent to invoke it for broad editing requests and to take priority over a related skill, which may shift a generic cleanup request into an AI-sign removal rewrite.
Trigger even for "clean this up" or "this reads like ChatGPT". ... Supersedes the humanizer skill when both could apply.
When using it, state whether you want light copyediting, a conservative rewrite, or a full de-AI reconstruction.
Using the rewritten output in settings with authorship or AI-use disclosure rules could create policy or trust problems.
The skill explicitly aims to make AI-like text appear human to detectors and readers; this is disclosed and purpose-aligned, but users should understand the potential for misuse or misrepresentation.
The result should pass both automated detectors and experienced human readers.
Use it only for appropriate editing purposes and follow any disclosure, academic, workplace, or publication rules that apply.