Security audit
Security checks for vulnerabilities and agentic risk
This is a text-editing skill that rewrites AI-sounding prose, with no hidden code execution, network use, persistence, or credential handling found.
Before installing, treat this as an editor that may actively rewrite documents and style choices. Review diffs for factual accuracy, tone, and typography preferences, especially if preserving exact wording or regional style matters.
The phrase "Or invoke directly when editing documents" does not define specific trigger phrases, scope limits, or exclusion conditions. Because it describes activation in a very broad context, it could cause unintended invocation during ordinary document editing activity.
The manifest says to use the skill when 'editing or reviewing text,' which is a very common and expansive context rather than a narrowly scoped trigger. The file does not provide explicit trigger phrases, boundaries, or negative examples to clarify when the skill should or should not activate, increasing the chance of unintended invocation.
The skill instructs the agent to replace curly quotation marks with straight quotes as a general rule, which imposes a specific typography/locale convention rather than preserving user or regional style preferences. The document does not offer an opt-in choice or limit this behavior to a justified house style.
No suspicious patterns detected.
