md2view
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python and Node.js scripts (
parse_blocks.py,verify_anchors.py,build_reader.py,shot.js) to parse, verify, and build document visualizations. This is a core part of the skill's functionality for generating local reader files. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Markdown input to generate a visualized HTML reader. It contains a robust mitigation strategy through the
verify_anchors.pyscript, which performs static analysis on the model-generated content to forbid<script>tags, , external resource loading (links/images), and CSS-based text obfuscation. Every piece of visualized content is strictly verified against the source Markdown using lexical anchors and number matching. - [EXTERNAL_DOWNLOADS]: The documentation suggests the installation of
playwrightvianpmto facilitate an automated screenshot-based self-review process. Playwright is a well-known and trusted library for browser automation and testing.
Audit Metadata