spring-boot-standard-crud
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requests and utilizes the Bash tool to verify the contents of the project's pom.xml file and to apply configuration properties to application.properties or application.yml files.
- [SAFE]: The generated code examples and instructions incorporate Jakarta validation constraints such as @NotBlank, @Positive, and @PositiveOrZero to ensure that incoming data is validated at the model level.
- [PROMPT_INJECTION]: The skill scaffolds Java code by interpolating user-specified entity names and attributes into predefined templates, which constitutes a functional surface for indirect prompt injection.
- Ingestion points: Entity names and field definitions provided by the user in SKILL.md.
- Boundary markers: No delimiters or isolation instructions are provided to distinguish user input from the core system prompts.
- Capability inventory: The skill has the ability to read, write, and edit project files and execute shell commands through the Bash tool for environment configuration.
- Sanitization: Input sanitization or filtering of user-provided strings is not explicitly detailed in the implementation instructions.
Audit Metadata