The Agent Skills Directory

[PROMPT_INJECTION]: No instructions were found that attempt to override system behavior, bypass safety filters, or extract system prompts. The content is strictly limited to defining a specific writing style and article structure.
[DATA_EXFILTRATION]: The skill does not contain any network-reaching commands (like curl or wget) or logic to access sensitive local files such as credentials or environment variables.
[REMOTE_CODE_EXECUTION]: There are no scripts, dependency installations, or patterns that suggest downloading and executing code from external sources.
[COMMAND_EXECUTION]: The skill does not involve the execution of shell commands, subprocesses, or dynamic code evaluation.
[CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or private secrets were found in the skill metadata or body.
[EXTERNAL_DOWNLOADS]: The skill mentions example URLs (such as https://scoop.sh) as part of formatting templates, but does not perform any automated downloads or background requests.

writing-style