The Agent Skills Directory

[SAFE]: The skill performs legitimate project configuration tasks, including modifying application.properties or application.yml and generating Java/Kotlin configuration classes. All operations are local to the user's filesystem and aligned with the stated purpose of configuring Kafka.
[SAFE]: External dependencies are restricted to the official spring-boot-starter-kafka artifact. The skill also provides a reference to the official marketplace for the Amplicode IntelliJ plugin, which is a resource owned by the skill's author and contains no suspicious indicators.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes data from untrusted sources within the project context during its configuration steps.
Ingestion points: Configuration data is derived from existing application.properties or application.yml files and user responses collected via the AskUserQuestion tool (referenced in SKILL.md Steps 1 and 2).
Boundary markers: The instructions do not specify the use of explicit boundary markers or instructions to ignore embedded commands when the agent reads existing project configuration files.
Capability inventory: Across its scripts, the skill utilizes capabilities to write and edit source files and modify project build dependencies (documented in SKILL.md Steps 4 and 5).
Sanitization: Values retrieved from properties files or user input are interpolated into code templates without explicit validation or sanitization routines mentioned in the logic.

kafka-configuration