The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the project's source code, specifically through the get_entity_details and list_class_members tool calls in SKILL.md. This data is used to generate mapping logic and determine build file modifications.
Ingestion points: Data enters the agent context via get_entity_details(entityFqn) and list_class_members(dtoFqn) calls in Step 2 of SKILL.md.
Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions when processing the content of these files.
Capability inventory: The skill utilizes an Edit tool to modify project build files (pom.xml, build.gradle, build.gradle.kts) and generates new Java/Kotlin source files.
Sanitization: Absent. There is no mention of escaping or validating the content of the read class members before interpolating them into the mapper templates.
[COMMAND_EXECUTION]: The skill is designed to programmatically modify core project configuration files. In Step 5 of SKILL.md, it instructs the agent to use the Edit tool to insert MapStruct dependencies (org.mapstruct:mapstruct and org.mapstruct:mapstruct-processor) into the build.gradle, build.gradle.kts, or pom.xml files based on the project's build system.

mapper-creator