markmap-viz
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted markdown data through several visualization tools.
- Ingestion points: Untrusted data enters the agent context through the markdown_content and outline_items parameters, and via local files read through the markmap_render_file tool.
- Boundary markers: The skill lacks explicit boundary markers or instructions telling the agent to ignore instructions embedded within the data it processes.
- Capability inventory: The skill includes file system read access through markmap_render_file and file system write access via the output_path parameter.
- Sanitization: There is no mention of sanitizing or validating the markdown content for malicious instructions or XSS vectors before rendering.
- [COMMAND_EXECUTION]: The tool calls use a shell execution pattern to invoke a Node.js script stored in the environment variable MARKMAP_MCP_SCRIPT. While standard for this platform, it relies on the script path being securely managed.
Audit Metadata