The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is designed to execute various system commands, including sdk for environment management, java for version checking, spring for project initialization, and ./mvnw for project verification. These actions are performed to bootstrap a development environment and verify the integrity of the generated project.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the user that is subsequently used in CLI operations, creating a potential injection surface.
Ingestion points: Project coordinates such as group-id, artifact-id, name, package-name, and dependencies are collected from user input as described in Step 1 of the reference file.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the user-provided strings were identified.
Capability inventory: The skill has the capability to execute shell commands via the spring init command and the Maven wrapper (./mvnw) as detailed in Steps 4 and 5 of the reference file.
Sanitization: There is no mention of validation or sanitization for the user-provided parameters before they are interpolated into the shell command strings.

300-frameworks-spring-boot-create-project