The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions require the agent to execute shell commands such as ./mvnw compile, mvn compile, ./mvnw clean verify, and mvn clean verify. These commands involve executing local scripts and build tools that can perform arbitrary actions on the host system depending on the project configuration.
[PROMPT_INJECTION]: The skill is designed to parse and act upon external Gherkin .feature files provided in the context. This creates an indirect prompt injection surface where a malicious file could contain instructions designed to manipulate the agent's code generation or influence the execution of build commands.
Ingestion points: External Gherkin .feature files.
Boundary markers: None identified in the processing logic.
Capability inventory: Full shell command execution via Maven build tools.
Sanitization: No evidence of sanitization or validation of the .feature file content before processing.
[EXTERNAL_DOWNLOADS]: The skill references and encourages the use of external libraries including Testcontainers and WireMock. These are well-known, industry-standard tools for Java testing and are typically fetched from official package registries.

323-frameworks-spring-boot-testing-acceptance-tests