The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes subprocess.run to call the Pandoc binary. Arguments are passed as a list rather than a single shell string, which is a security best practice that prevents shell injection attacks.\n- [EXTERNAL_DOWNLOADS]: The documentation includes installation instructions for Pandoc and its Python wrapper pypandoc. These tools are fetched from well-known and trusted sources, including system package managers (Homebrew, APT, Chocolatey) and the PyPI registry.\n- [DATA_EXFILTRATION]: No evidence of unauthorized data access or network transmission was found. The skill documentation includes placeholders (e.g., YOUR_API_KEY) for sensitive information within templates, which is a safe and standard practice.\n- [PROMPT_INJECTION]: The instructions and metadata are strictly focused on document conversion tasks and do not contain any patterns intended to bypass safety filters or override agent behavior.

md-to-office