excalidraw-diagram
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to generate diagrams, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: Processes text content from user inputs to identify concepts and relationships as defined in SKILL.md.
- Boundary markers: The skill does not define specific delimiters or instructions to the agent to ignore potentially malicious instructions embedded within the user data.
- Capability inventory: The skill is instructed to automatically save generated diagrams to the local filesystem using a write tool (SKILL.md).
- Sanitization: While the skill performs character replacement for format compatibility (e.g., replacing quotes and parentheses), it does not implement security-focused sanitization or validation of the input content.
- [EXTERNAL_DOWNLOADS]: The skill references external services for Excalidraw functionality, including the official web platform at excalidraw.com and a community animation tool hosted on GitHub Pages.
Audit Metadata