Security audit
Security checks for vulnerabilities and agentic risk
This is a document-editing skill whose main risk is misuse to disguise AI-written text, but the artifact does not show hidden execution, exfiltration, or persistence.
Use this only for legitimate editing and readability improvements. Do not use it to evade school, workplace, publication, legal, or platform disclosure rules about AI assistance, and review changes before allowing it to write back to files.
The phrase "Or invoke directly when editing documents" does not define specific trigger phrases, contexts, or exclusion conditions. In a markdown skill description, this kind of broad activation guidance can overlap with common editing activity and makes it unclear when the skill should or should not run.
The skill explicitly aims to remove signs of AI-generated writing and make text appear human-written, which can facilitate deceptive disclosure practices in academic, journalistic, compliance, or customer-facing contexts. While the file does not contain code execution or data exfiltration behavior, the core functionality encourages concealment of AI assistance without requiring user justification, transparency, or policy checks.
No suspicious patterns detected.
