md2pdf
Warn
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the user to execute a local Python script (
scripts/md2pdf.py) and modify its file permissions usingchmod +x. It also recommends usingsudo apt installto install required system libraries (libpango) on Linux-based systems. - [EXTERNAL_DOWNLOADS]: The documentation references official package managers, including Homebrew for macOS and the APT registry for Ubuntu/Debian, for installing necessary system libraries and fonts.
- [PROMPT_INJECTION]: The skill processes untrusted Markdown content to generate PDF output, which presents a surface for indirect prompt injection attacks targeting the conversion process.
- Ingestion points: Input Markdown files (
input.md) provided by the user or external sources. - Boundary markers: The documentation does not specify the use of delimiters or boundary instructions to isolate processed content.
- Capability inventory: The conversion process involves file system operations (read/write) and utilizes the WeasyPrint engine, which may fetch remote assets (images, stylesheets) if referenced in the Markdown input.
- Sanitization: No information is provided regarding input sanitization or validation of the Markdown content before it is processed by the PDF engine.
Audit Metadata