md-render
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The template includes a script reference to the Mermaid.js library hosted on the jsDelivr CDN (cdn.jsdelivr.net) to provide diagram rendering capabilities.
- [COMMAND_EXECUTION]: The bash script uses
openorxdg-opento launch the generated HTML file in the user's default web browser. - [PROMPT_INJECTION]: The skill implements an indirect prompt injection surface by rendering markdown content with HTML support enabled.
- Ingestion points: Reads markdown data from local files or standard input via the
md-rendershell script. - Boundary markers: No explicit delimiters or instructions are provided to the model to ignore embedded commands within the processed markdown content.
- Capability inventory: The skill has the ability to write to the local filesystem and execute system commands to open a web browser.
- Sanitization: The
markdown-itrenderer is configured withhtml: true, allowing raw HTML and potential scripts within the input markdown to be included in the final rendered output.
Audit Metadata