The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to instructions embedded in the external data it is designed to process, such as JIRA stories and OpenAPI specifications.
Ingestion points: SKILL.md and README.md specify that the agent should use provided JIRA stories, OpenAPI/spec details, and acceptance criteria as context for code generation.
Boundary markers: Absent. The instructions do not define specific delimiters or warnings to ignore instructions within the ingested data.
Capability inventory: The skill enables the agent to write and modify Java code files, including controllers, services, and downstream clients, as well as build configuration files like pom.xml.
Sanitization: Absent. The skill explicitly directs the agent to treat external contracts as the "source of truth" without requiring validation of the input instructions.
[SAFE]: The skill incorporates security best practices by explicitly instructing the agent to avoid hardcoding environment-specific values like credentials in constants and to prevent data leakage by not logging full downstream error responses.

generate-api-code