mermaid-diagrams
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted natural language or technical descriptions to generate diagram source code and suggests execution of conversion tools.
- Ingestion points: The skill extracts entities and relationships from user-provided descriptions (SKILL.md).
- Boundary markers: No delimiters or specific instructions to ignore embedded commands are present in the workflow.
- Capability inventory: The skill produces Mermaid source code, suggests shell commands for export, and provides Node.js snippets (SKILL.md).
- Sanitization: No input validation or sanitization is performed on the user-provided descriptions.
- [EXTERNAL_DOWNLOADS]: The skill recommends using the
@excalidraw/mermaid-to-excalidrawpackage from a well-known service for diagram conversion. - [COMMAND_EXECUTION]: Provides a pre-configured CLI command (
npx @excalidraw/mermaid-to-excalidraw) to the user for converting diagram formats.
Audit Metadata