excalidraw-diagram-generator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided JSON data from Excalidraw files and libraries, which represents an ingestion surface for indirect prompt injection. \n
- Ingestion points:
scripts/split-excalidraw-library.py(reads.excalidrawlibfiles) andscripts/add-icon-to-diagram.py(reads.excalidrawfiles). \n - Boundary markers: No explicit delimiters are used in the processed JSON files. \n
- Capability inventory: The bundled Python scripts perform file system operations including reading, writing, renaming, and deleting files. \n
- Sanitization:
scripts/split-excalidraw-library.pyuses regular expressions to sanitize filenames, andscripts/add-icon-to-diagram.pyregenerates all element IDs to prevent conflicts. \n- [COMMAND_EXECUTION]: The skill relies on local Python scripts to handle diagram modifications and icon library processing, which is an expected and functional part of the skill's design.
Audit Metadata