editorial-diagram
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to utilize platform-specific system commands such as open, xdg-open, and start to open or export generated diagram files using the draw.io CLI. These are standard operations for file management within the skill's intended workflow.
- [DYNAMIC_EXECUTION]: The skill executes a local Python script, scripts/validate_drawio.py, to perform structural validation of the generated XML content. The script uses standard libraries for XML parsing and does not perform unsafe operations like remote code execution or dynamic evaluation of untrusted code.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text as input for diagram generation, which presents a surface for indirect prompt injection. The instructions mitigate this risk by providing specific quality checks and guidance on escaping special characters like <, >, and & within the generated XML to ensure data integrity.
Audit Metadata