markmap-viz
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted markdown data (e.g., network logs, audit results) to generate visualizations, creating an indirect prompt injection surface.
- Ingestion points: The
markdown_contentandoutline_itemsparameters across multiple tools inSKILL.mdaccept external data. - Boundary markers: The documentation does not specify delimiters or instructions for the agent to ignore instructions embedded within the markdown content.
- Capability inventory: The skill can read local files (
markmap_render_file) and execute a Node.js script through the MCP interface. - Sanitization: No input validation or sanitization of the markdown content is indicated before it is passed to the rendering engine.
- [COMMAND_EXECUTION]: The skill documentation describes executing a Node.js script via an environment variable (
MARKMAP_MCP_SCRIPT) using the$MCP_CALLutility. This facilitates the execution of local code to perform visualization tasks.
Audit Metadata