The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run Maven build commands such as ./mvnw compile and mvn clean verify in the SKILL.md workflow to ensure code correctness during refactoring tasks. These are standard developer tools used for their intended purpose within a Java development environment.
[INDIRECT_PROMPT_INJECTION]: The skill has a potential vulnerability surface as it processes user-provided Java code and executes Maven commands on the project. 1. Ingestion points: The skill acts on user-supplied source code and project configurations. 2. Boundary markers: The instructions do not define specific delimiters or security boundaries for the code being processed. 3. Capability inventory: The skill utilizes shell access to execute Maven build and test cycles. 4. Sanitization: The skill assumes the project's build scripts and environment are safe and does not perform explicit validation of Maven configuration files.

123-java-design-patterns