Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward technical blog-writing helper that creates a standalone HTML article file, with no evidence of hidden execution, credential access, network use, or persistence beyond the requested output file.
Install this if you want blog posts generated as standalone local HTML files. Check the output path and filename before use if overwriting files matters, and specify the desired language in your prompt if you do not want Chinese-language output.
The instructions are written to produce content as a Chinese-language technical blog writer and do not provide a user opt-in or alternative language behavior. This can violate language/locale policy because it imposes a specific language regardless of user preference.
The skill explicitly instructs the agent to render output to a standalone HTML file, which is a filesystem write side effect, without any requirement for user consent, confirmation, or clear disclosure. In an agent environment with file-write capability, this can cause unexpected persistence of generated content, overwriting existing files, or creating artifacts the user did not intend to store.
