excalidraw-diagram
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes untrusted user-supplied text to generate structured Excalidraw data and uses a file-writing tool to save files locally.
- Ingestion points: The agent analyses user content (flowcharts, mind maps, concepts) to build the diagram elements.
- Boundary markers: The skill provides a rigid Markdown and JSON template for the output, though it does not explicitly instruct the agent to ignore instructions embedded within the user text.
- Capability inventory: The skill directs the agent to utilize a 'Write' tool to automatically save files to the filesystem.
- Sanitization: The skill mandates a '.md' extension and specifies the current working directory, which reduces the risk of writing malicious executable scripts, but it does not provide explicit protection against path traversal attacks in the user-generated filename.
Audit Metadata