The Agent Skills Directory

[PROMPT_INJECTION]: The skill instructions and documentation are purely educational and professional. There are no attempts to override agent behavior, bypass safety filters, or extract system prompts.
[DATA_EXFILTRATION]: No network-enabled tools or commands are present. The Python script in scripts/process.py only performs local data processing and calculations. No hardcoded credentials or sensitive file paths were detected. All sample data (CNPJ, addresses) used in templates are standard Brazilian placeholders for a fictional entity.
[REMOTE_CODE_EXECUTION]: There are no remote code downloads or execution patterns. The skill does not use curl | bash, wget, or any mechanisms to fetch external scripts.
[COMMAND_EXECUTION]: No dangerous system commands or privilege escalation attempts (sudo, chmod) are present. The provided Python script uses only standard libraries for data formatting and date calculations.
[OBFUSCATION]: All content is provided in clear, plain text. No Base64 encoding, zero-width characters, homoglyphs, or other obfuscation techniques were found.
[EXTERNAL_DOWNLOADS]: The skill does not define any external dependencies or download any third-party packages. It operates entirely with local markdown and standard Python code.
[SAFE]: The skill matches its stated purpose as a compliance guide and utility. All scripts and templates are consistent with LGPD requirements (e.g., 15-day response deadlines, 10 lawful bases).

brazil-lgpd