Security audit
Security checks for vulnerabilities and agentic risk
This skill is a text editor, but its stated goal is to hide signs that writing was AI-generated without adding disclosure or misuse limits.
Install only if you want an editor that rewrites text for naturalness and you will use it on drafts you are allowed to edit. Do not use it to conceal AI authorship where disclosure is required, for academic dishonesty, impersonation, spam, or misleading provenance claims.
The skill explicitly aims to remove signs of AI-generated writing and make text sound human-written, but it includes no consent, disclosure, or use-policy constraints. That creates a direct pathway for deception, including plagiarism laundering, impersonation, spam optimization, and bypassing rules that rely on truthful disclosure of AI assistance.
The skill description is broad enough to activate on ordinary editing or review tasks, which increases the chance it will be invoked outside a narrow, user-intended context. Because the skill’s purpose is to rewrite text to appear more human-written, overbroad triggering can silently steer benign writing assistance into deceptive obfuscation workflows.
No suspicious patterns detected.
