spring-boot

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The scripts/verify.sh utility performs local static analysis by executing standard shell commands such as grep and sed. It is designed to identify legacy Spring Boot idioms in a project's source code and configuration files, operating exclusively on the local file system without network activity.\n- [PROMPT_INJECTION]: The skill processes user-supplied business requirements to generate Java backend code, creating an indirect prompt injection surface.\n
  • Ingestion points: User-provided specifications for REST endpoints, JPA entities, and security policies described in SKILL.md and evals/cases.yaml.\n
  • Boundary markers: Absent. The skill does not instruct the agent to use specific delimiters or ignore instructions embedded within user requirements.\n
  • Capability inventory: The agent can generate and write .java, .yml, and .sql files, and execute the provided verify.sh script.\n
  • Sanitization: The skill lacks explicit instructions for sanitizing or validating the content of user-provided requirements before their inclusion in the generated code or configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 09:37 PM
Security Audit — agent-trust-hub — spring-boot