The Agent Skills Directory

[PROMPT_INJECTION]: The skill body consists entirely of technical documentation and code examples for Kotlin development. No attempts to override system prompts, bypass safety filters, or use adversarial role-play patterns were detected.
[DATA_EXFILTRATION]: The skill does not access sensitive local files or environment variables. It includes a standard placeholder URL https://api.example.com within a code example for educational purposes, which is a safe practice.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the download and execution of remote scripts or the installation of unverified packages. The Bash tool usage is correctly scoped to kotlin and gradle commands in the metadata.
[OBFUSCATION]: The text and code are presented in clear, plain text. Analysis for Base64, zero-width characters, homoglyphs, and hidden text patterns returned no results.
[INDIRECT_PROMPT_INJECTION]: The skill provides static documentation and does not ingest untrusted external data for runtime processing, eliminating this attack surface.

kotlin-expert