excalidraw-diagrams
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill converts user-provided text into visual diagram structures, which is the primary purpose of the skill.
- Ingestion points: Analysis of user content in SKILL.md process step 2.
- Boundary markers: No explicit markers are defined to separate user input from system instructions.
- Capability inventory: Writing generated diagram files to the local file system.
- Sanitization: No explicit sanitization of input text before inclusion in the diagram is specified.
- [SAFE]: The skill includes robust safeguards for file management, including mandatory confirmation for paths and filenames, and checking for existing files before overwriting. The use of official repositories and domains for diagram source attribution is consistent with safe behavior.
Audit Metadata