The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands including Maven (mvn), Gradle (./gradlew), and Git to perform project build, test, and verification tasks.
[EXTERNAL_DOWNLOADS]: During the build and testing phases, dependencies are fetched from Maven Central and a PostgreSQL Docker image is retrieved from Docker Hub via Testcontainers.
[PROMPT_INJECTION]: The skill ingests untrusted data from the local project's source code, configuration files, and git history, creating an indirect prompt injection surface. The ingestion points include the src directory and pom.xml/build.gradle files; no explicit boundary markers or sanitization are defined, although this is a standard risk for development-focused agents and results in a low security impact.

springboot-verification