spring-boot
Warn
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: MEDIUMCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The SKILL.md file contains a hardcoded string "SecretKey012345678901234567890123456789" for the security.session.jwt.secret configuration in Part 8. Although provided as a template example, such hardcoded secrets can be easily copied into production code, leading to weak authentication security.
- [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by instructing the agent to build controllers that process external user input.
- Ingestion points: User input is accepted via UserForm and UserPageQuery objects in the UserController (documented in SKILL.md).
- Boundary markers: There are no instructions provided to use delimiters or warnings to ignore embedded instructions in the ingested data.
- Capability inventory: The generated code includes database operations via SysUserMapper and transaction management in UserServiceImpl.
- Sanitization: While standard Java @Valid annotations are used for data validation, there is no mention of sanitizing input to prevent instructions from influencing subsequent agent actions if the data is processed by an LLM.
Audit Metadata