The Agent Skills Directory

[SAFE]: The skill provides structured guidance for Kotlin development. It contains no executable scripts, network operations, or requests for sensitive filesystem access. The provided JSON and Markdown files are purely informational or configuration-based for static analysis and evaluation purposes.
[INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it processes user-supplied Kotlin code for review. While this is a potential vector for indirect prompt injection (e.g., instructions hidden in code comments), the skill does not possess sensitive capabilities like network exfiltration or system command execution that could be exploited. The instructions clearly define a structured output format for reviews, which helps maintain the agent's persona.

effective-kotlin