baoyu-markdown-to-html

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted Markdown content and converts it into styled HTML. It supports complex rendering such as Mermaid diagrams via headless Chrome.
  • Ingestion points: The input Markdown file processed in scripts/main.ts.
  • Boundary markers: The skill does not implement explicit boundary markers or instructions to ignore embedded prompts in the source Markdown.
  • Capability inventory: The skill performs file system reads and writes (fs.readFileSync, fs.writeFileSync, fs.renameSync), network requests to fetch external images, and utilizes a headless browser for rendering diagrams.
  • Sanitization: Employs standard Markdown parsing via baoyu-md and provides HTML attribute escaping for image tags during output generation.
  • [COMMAND_EXECUTION]: The instructions command the agent to execute shell commands using bun or npx to run the conversion script.
  • [EXTERNAL_DOWNLOADS]: The conversion script includes functionality to detect, fetch, and locally store remote images referenced via HTTP/HTTPS URLs in the input Markdown file.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 07:47 AM
Security Audit — agent-trust-hub — baoyu-markdown-to-html