excalidraw-diagram-generator
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation refers to downloading icon libraries from libraries.excalidraw.com, which is a well-known community resource for Excalidraw.
- [COMMAND_EXECUTION]: The skill uses Python scripts (add-arrow.py, add-icon-to-diagram.py, split-excalidraw-library.py) to perform structured modifications to Excalidraw diagram files. These scripts rely on standard library modules and are executed locally by the agent to maintain diagram integrity and token efficiency.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes user-provided descriptions and potentially untrusted external icon library files.
- Ingestion points: User prompts for diagram generation and third-party .excalidrawlib files (e.g., in SKILL.md and split-excalidraw-library.py).
- Boundary markers: Absent; the skill relies on the agent's interpretation of data.
- Capability inventory: File system read/write operations for .excalidraw and JSON files (add-arrow.py, add-icon-to-diagram.py, split-excalidraw-library.py), and local script execution.
- Sanitization: Filename sanitization is performed during library splitting in split-excalidraw-library.py to prevent path traversal or invalid file creation.
Audit Metadata