spring-boot-crud-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted entity specifications to generate Java code. * Ingestion points: The
scripts/generate_crud_boilerplate.pyscript loads data from a spec file provided via the--specargument. * Boundary markers: The script does not use specific delimiters to separate untrusted data within the prompt, though it expects structured JSON/YAML. * Capability inventory: The script has the capability to write files to the filesystem using theWritetool and Python's file operations. * Sanitization: The script performs regex validation on the entity name and checks field types against a whitelist of supported Java types. - [COMMAND_EXECUTION]: The skill includes a Python script
scripts/generate_crud_boilerplate.pyfor scaffolding project files. The script is a standard development tool and does not contain malicious commands.
Audit Metadata