The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands, specifically ./mvnw compile, mvn compile, ./mvnw clean verify, and mvn clean verify, to ensure the project remains in a valid state during refactoring.
[INDIRECT_PROMPT_INJECTION]: The skill processes project source code and build configuration files, which could potentially contain malicious instructions if the project itself is untrusted.
Ingestion points: The agent reads and analyzes existing Java source files and Maven pom.xml files within the workspace as described in the workflow section of SKILL.md.
Capability inventory: The agent has the capability to execute shell-based build tools (mvn, mvnw) as per the constraints in SKILL.md.
Boundary markers: The skill does not define specific delimiters or warnings to ignore instructions embedded within the codebase being tested.
Sanitization: There is no evidence of sanitization or validation of the contents of the project files before they are processed by build tools.

421-frameworks-quarkus-testing-unit-tests