skills/giuseppe-trisciuoglio/developer-kit-claude-code/spring-boot-crud-patterns/Gen Agent Trust Hub
spring-boot-crud-patterns
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements its stated functionality using standard template-based code generation. No suspicious network operations, hardcoded credentials, or obfuscated code were found. The tool scaffolds feature-based architecture for Spring Boot 3 applications, separating domain, application, and infrastructure layers according to established architectural patterns. All operations are local and triggered by explicit agent actions.\n- [PROMPT_INJECTION]: The skill processes external entity specifications (JSON/YAML) via the generate_crud_boilerplate.py script. This presents an indirect prompt injection surface where instructions could be hidden in metadata or field names within the specification file. However, the script uses string.Template.safe_substitute for interpolation, which mitigates direct code execution risks during the rendering process.\n
- Ingestion points: scripts/generate_crud_boilerplate.py reads file content from the --spec argument provided at runtime.\n
- Boundary markers: Not explicitly implemented in the template rendering logic.\n
- Capability inventory: The skill has access to Write, Bash, and Edit tools, allowing it to modify the filesystem based on user input.\n
- Sanitization: Identifier names are validated for PascalCase format to ensure they represent valid Java class names, but the script otherwise relies on the integrity of the provided specification file.
Audit Metadata