create-spring-boot-kotlin-project

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs inserting plaintext credentials (e.g., "rootroot", database usernames/passwords) into application.properties and docker-compose, requiring the LLM to emit secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.75). The skill downloads a Spring Initializr ZIP from https://start.spring.io/starter.zip at runtime and unzips it, so the LLM may ingest the downloaded project’s text files (e.g., generated source/config) as free-form content from an outsider source (public web content).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill runs a runtime curl to fetch a remote project template (https://start.spring.io/starter.zip) which the user then builds/runs with Gradle, meaning remote code/content is fetched at runtime and executed as a required dependency.