Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed writing editor for making text sound less AI-generated, with no code execution, network use, credential access, or persistence found.
Install only if you want an agent to rewrite text for a more natural style. Use it on documents you are authorized to edit, and do not use it to misrepresent authorship where disclosure rules, academic policies, workplace policies, or publication standards require transparency.
The phrase "Or invoke directly when editing documents" does not specify what exact trigger phrases, contexts, or exclusions activate the skill. In a markdown skill description, this ambiguity can cause unintended invocation during ordinary document-editing workflows.
The skill explicitly instructs the agent to make text sound more human-written and to 'remove signs of AI-generated writing,' which can enable deceptive authorship masking if used without clear user consent or disclosure. While framed as an editing aid, the functionality materially helps users evade AI-detection heuristics and impersonate human authorship, making the static finding valid in context.
No suspicious patterns detected.
