The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to verify the state of the project. Specifically, it requires running ./mvnw compile or mvn compile before applying changes and ./mvnw clean verify or mvn clean verify afterward, as documented in SKILL.md and references/413-frameworks-quarkus-db-migrations-flyway.md. These are standard build operations for the intended development context.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external project data, which introduces a potential surface for indirect instructions to influence agent behavior.
Ingestion points: According to SKILL.md and the reference files, the skill reads project metadata, build configuration (pom.xml), application properties (application.properties), and database migration scripts (src/main/resources/db/migration/*.sql).
Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the content read from the user's project files.
Capability inventory: The skill allows the agent to execute shell commands via Maven and modify critical project files (build configuration, application settings, and SQL scripts) as described in the Workflow section of SKILL.md.
Sanitization: There are no explicit requirements for sanitizing or escaping the content of the SQL scripts or configuration values before they are processed or interpolated into the agent's context.

413-frameworks-quarkus-db-migrations-flyway