The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a Python script scripts/writing_helper.py which performs text analysis, keyword extraction, and readability checks. The script uses standard libraries and only processes text provided through standard input, with no access to the shell or external commands.
[DATA_EXFILTRATION]: There are no network operations, API calls, or data transmission patterns detected in the instructions or the Python script.
[PROMPT_INJECTION]: The prompts provided in SKILL.md and references/prompt_templates.md use specific personas (e.g., a 'cold and mean content editor') to guide the AI's behavior for editing purposes. These are standard instructional techniques and do not attempt to bypass safety filters or override core system instructions.
[REMOTE_CODE_EXECUTION]: No external dependencies are downloaded or executed. The Python script is local and does not use dangerous functions like eval() or exec().
[DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths (like .ssh or .env), or unauthorized data access patterns were found.

ai-writing-assistant