The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local build wrappers to perform project verification and testing.
Evidence: SKILL.md contains instructions to execute ./mvnw verify, ./mvnw verify -pl <module>, and ./gradlew check to confirm code quality and security configuration.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes project structure and dependencies, creating a surface where malicious instructions in project files could influence the agent.
Ingestion points: SKILL.md instructs the agent to review project structure, dependencies, and Spring configuration as the first step of the core workflow.
Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading project files.
Capability inventory: The agent has capabilities to execute shell commands (mvnw, gradlew) and modify project source files.
Sanitization: The instructions do not specify validation or sanitization of data retrieved from the project environment.

java-architect