diagram-generator

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/main.cjs uses child_process.spawn to execute a local script generate.mjs within the skill's directory structure. This facilitates the delegation of complex diagramming logic to a specialized helper file.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface.\n
  • Ingestion points: Local codebase files are scanned using Read, Glob, and Grep tools to identify architectural patterns and relationships.\n
  • Boundary markers: No specific delimiters or directives are used to separate the content of the analyzed files from the model's instructions.\n
  • Capability inventory: The skill has broad read/write access to the filesystem and can execute local Node.js scripts via spawn.\n
  • Sanitization: There is no evidence of content sanitization or validation for the data extracted from the project codebase before it is processed by the underlying model for diagram generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 07:55 AM