zukai-creator
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions (SKILL.md) and supporting references are focused on conceptual diagramming and do not contain any obfuscated content, hardcoded credentials, or malicious prompt injection patterns.- [SAFE]: The skill includes a local validation script (
scripts/check-diagram-brief.py). Analysis confirms the script uses standard Python libraries (json, sys, pathlib) for structural data validation and does not perform any network operations, unsafe dynamic execution, or unauthorized file access.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided source text and JSON files to generate diagrams, representing a potential ingestion surface for indirect prompt injection. However, the risk is minimal as the skill implements structural validation via its internal Python script to ensure data integrity before processing.
Audit Metadata