The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed for reviewing, building, and writing Kotlin code, which inherently involves processing untrusted data from source files, pull request bodies, or external API data encountered during development and debugging.
Ingestion points: The agent ingests content from project source files, configuration files (Gradle/Maven), and potentially external API responses or documentation during the development lifecycle.
Boundary markers: The instructions do not specify the use of clear delimiters (e.g., XML tags or triple backticks) to separate untrusted project content from the agent's core instructions.
Capability inventory: The skill allows the agent to generate code, write files, and execute static analysis tools like detekt and ktlint.
Sanitization: There is no evidence of specific sanitization or escaping mechanisms for external content interpolated into the agent's prompts.

kotlin-specialist