spring-boot-core
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process Spring Boot source code, build configurations, and architectural designs provided by users, which creates an attack surface for instructions embedded in data.
- Ingestion points: User-provided Java source files, Maven pom.xml or Gradle build.gradle files, and JPA/Hibernate entity mappings.
- Boundary markers: The routing instructions do not define explicit delimiters or warnings to ignore embedded instructions in the processed data.
- Capability inventory: The skill allows the agent to generate new code slices, audit existing code, and configure security components like filters and authentication providers.
- Sanitization: The skill advocates for the use of Jakarta Bean Validation and RFC 7807 ProblemDetail responses to sanitize and validate external inputs at the application level.
- [NO_CODE]: The skill folder contains only markdown documentation and reference files (SKILL.md and files in references/) without any executable shell scripts, Python scripts, or compiled binaries.
Audit Metadata