baoyu-markdown-to-html

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions in SKILL.md direct the agent to execute the conversion logic via scripts/main.ts using the bun or npx runtime.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted markdown files provided by the user, which serves as a potential vector for indirect instructions.
  • Ingestion points: The entry script scripts/main.ts reads the full content of the input markdown file provided by the user.
  • Boundary markers: The skill does not implement specific delimiters or "ignore instructions" wrappers for the raw markdown content before it is parsed by the underlying libraries.
  • Capability inventory: The script performs file system operations such as writing HTML results (fs.writeFileSync), renaming files for backup (fs.renameSync), and creating temporary directories for image resolution (fs.mkdtempSync).
  • Sanitization: While the tool uses standard markdown parsing libraries (baoyu-md which wraps marked and remark) and escapes HTML attributes, the processed body content remains an interpolation surface for external data.
  • [DYNAMIC_EXECUTION]: The skill supports rendering Mermaid diagrams from the input markdown. This process involves executing code within a headless Chrome instance via the baoyu-chrome-cdp library to generate PNG assets.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 09:25 AM