create-spring-boot-java-project

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt embeds plaintext credentials (e.g., "rootroot", DB usernames) and instructs the agent to place them verbatim into application.properties and docker-compose.yaml, requiring the LLM to handle and output secret values directly.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The runtime workflow downloads a Spring Boot template from the public web (curl https://start.spring.io/starter.zip), unzips it, and thus ingests outsider-authored free text (the template’s files/content) into the agent’s context when it processes the downloaded project.