Security audit
Security checks for vulnerabilities and agentic risk
This is a text-editing skill that rewrites AI-sounding prose, with no evidence of hidden execution, exfiltration, persistence, or unrelated privileged behavior.
Install this if you want an agent to help revise prose to sound less AI-generated. Because it has Write/Edit permissions, use it on documents where file changes are expected, and ask the agent to show proposed edits first for important or sensitive text.
The manifest says to use the skill when 'editing or reviewing text,' which is a very common, expansive context rather than a specific trigger. It does not define narrower invocation phrases, boundaries, or exclusion cases, so the skill could be selected in many ordinary writing situations unintentionally.
The skill is granted Write and Edit capabilities, but the description and instructions do not clearly warn that it may directly modify files. In an editing workflow, that can cause unintended changes to user content if the agent invokes the skill proactively or applies rewrites without explicit confirmation, especially because the skill's process encourages producing revised drafts and final versions.
No suspicious patterns detected.
