design-architect
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends the installation of the
@mermaid-js/mermaid-clipackage from the official NPM registry to facilitate PNG and SVG conversion. - [COMMAND_EXECUTION]: Provides instructions for using the
mmdccommand-line tool to process Mermaid files. This includes basic conversion commands and shell loops for batch processing of diagram files. - [DATA_EXPOSURE]: Defines a clear directory structure for output files under
.workflow/architect/, ensuring that generated artifacts are organized within the project environment. - [INDIRECT_PROMPT_INJECTION]: The skill features an attack surface for indirect prompt injection as it ingests user-provided architecture requirements to generate code and files.
- Ingestion points: User requirements collected during the 'Requirement Gathering' phase in
SKILL.md. - Boundary markers: None explicitly defined to separate user input from the Mermaid syntax generation.
- Capability inventory: File system writes (.md, .png, .svg) and execution of the
mmdcCLI. - Sanitization: No specific sanitization or validation of Mermaid syntax is described prior to file creation or rendering.
Audit Metadata