The Agent Skills Directory

NO_CODE (SAFE): The skill consists entirely of Markdown instructions and documentation frameworks. There are no executable scripts (Python, JavaScript, Shell) or configuration files that could perform actions on a system.- PROMPT_INJECTION (SAFE): No instructions were found that attempt to override the AI agent's safety filters, ignore previous instructions, or extract system prompts. The content is focused on technical writing standards.- DATA_EXPOSURE (SAFE): There are no hardcoded credentials, API keys, or references to sensitive local file paths.- EXTERNAL_DOWNLOADS (SAFE): No commands like curl, wget, or package manager installations (pip, npm) are present. The resource files listed are local relative paths within the skill's own directory structure.- INDIRECT_PROMPT_INJECTION (LOW): While the skill is designed to process user-provided content (code or drafts) to generate documentation, it lacks any autonomous write or execution capabilities. The risk is limited to the text output generated for the user.

doc-writing