The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional Markdown and configuration files (JSON/YAML) used to guide an AI agent in writing technical documentation. There are no executable scripts or binaries included.\n- [PROMPT_INJECTION]: Analysis of the instructions shows no attempts to bypass safety filters, override system prompts, or extract internal instructions. The focus remains on document classification and formatting.\n- [DATA_EXFILTRATION]: No network operations (curl, wget, etc.) or access to sensitive file paths (e.g., credentials) were found. The skill operates locally on provided text inputs.\n- [REMOTE_CODE_EXECUTION]: No remote code execution patterns or package manager installations (npm, pip) were detected.\n- [OBFUSCATION]: No obfuscated strings, hidden characters, or encoding techniques were found in any of the analyzed files.\n- [COMMAND_EXECUTION]: The skill does not attempt to execute shell commands or interact with the operating system beyond basic file operations permitted by the agent environment.

technical-writing