The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/generate_pdf.py executes the pandoc binary via subprocess.run. The command is constructed as a list of arguments, which is a secure implementation that avoids shell injection vulnerabilities. This execution is necessary for the skill's primary function of document conversion.
[EXTERNAL_DOWNLOADS]: The documentation references well-known and trusted software packages, specifically Pandoc and XeLaTeX. It provides standard installation instructions for these tools using official system package managers (brew and apt-get), which is considered safe practice for development tools.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied markdown files, which constitutes an attack surface for indirect prompt injection if the processed content contains malicious instructions designed to manipulate the agent's logic.
Ingestion points: Markdown file content is read and modified by scripts/fix_markdown.py and then passed to pandoc via scripts/generate_pdf.py.
Boundary markers: The processing scripts do not currently employ specific delimiters or 'ignore' markers to separate user data from instructions.
Capability inventory: The skill has the capability to write to the file system and execute the pandoc document converter.
Sanitization: The markdown preprocessor corrects formatting issues but does not validate or sanitize the text for potential logical injection patterns.

pdf-generation