markdown-to-pdf

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical guide for document generation. The provided Python scripts and shell commands are legitimate examples for the tools described.
  • [COMMAND_EXECUTION]: The skill includes shell command examples for the pandoc utility. These are used for converting Markdown files to PDF via standard input/output flags and are consistent with the skill's primary purpose.
  • [EXTERNAL_DOWNLOADS]: A code example demonstrates the ability to render a PDF from a remote URL using the WeasyPrint library. The example uses a generic domain (example.com) and represents standard functionality for web-to-PDF tools.
  • [SAFE]: The skill is designed to process untrusted external data (Markdown and HTML files) which is a potential surface for indirect prompt injection. However, given this is the core function of the skill, the risk is inherent and managed by the specific conversion toolchains.
  • Ingestion points: Reads content from local Markdown and CSS files, and optionally from a URL.
  • Boundary markers: None present in the provided templates.
  • Capability inventory: File system read/write access and local command execution via pandoc.
  • Sanitization: Standard library-based parsing is used (e.g., markdown.markdown, weasyprint.HTML), though no explicit sanitization for LLM instructions within the data is shown.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 07:28 PM
Security Audit — agent-trust-hub — markdown-to-pdf