The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the execution of Maven commands (mvn compile and mvn clean verify) to ensure the project is in a valid state before and after generating test code. These commands are standard for Java development environments and are used here for legitimate verification purposes.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes Gherkin .feature files provided in the context.
Ingestion points: External .feature files (e.g., Order.feature) are read to define test scenarios.
Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to ignore potentially malicious directions embedded within the Gherkin text.
Capability inventory: The agent is granted the capability to write Java source files and execute build commands (mvn) based on the content of these files.
Sanitization: No specific sanitization or filtering logic is prescribed for the input text.
Conclusion: This is considered a low-risk finding as it is inherent to the primary function of a BDD-based code generation tool.
[EXTERNAL_DOWNLOADS]: The skill references standard development libraries such as Quarkus, Testcontainers, and WireMock. These dependencies are resolved through standard build tools (Maven) from official package registries.

423-frameworks-quarkus-testing-acceptance-tests