The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected across the 11 threat categories during the audit of 84 files.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute remote code. The requirements.txt file specifies that only Python standard library modules are used, and the optional development tools listed (pytest, black, flake8) are standard industry utilities.
[DATA_EXPOSURE]: No hardcoded credentials, API keys, or sensitive file paths (such as SSH keys or AWS configs) were identified. The skill handles user input only to populate prompt templates.
[COMMAND_EXECUTION]: The automation scripts (generate_prompt.py, batch_generator.py, validator.py, optimizer.py) perform local file read/write operations and string manipulations using regular expressions. They do not invoke shell commands with untrusted user input or perform unauthorized system modifications.
[PROMPT_INJECTION]: While the skill is designed to generate complex prompts, it does not contain instructions aimed at bypassing agent safety filters or extracting system prompts. The generated prompts are intended for the user to copy and use in separate sessions.
[EXTERNAL_DOWNLOADS]: No external network requests or downloads from untrusted sources were found in the analyzed scripts or documentation.

prompt-factory