The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The scripts suggest-kmp-dependency.sh and validate-kmp-structure.sh use standard Unix utilities like grep, find, awk, and sed to analyze Kotlin source files and Gradle configurations. These operations are restricted to the local project directory and do not involve shell injection or dangerous command execution.
[DATA_EXFILTRATION] (SAFE): No network operations, hardcoded credentials, or access to sensitive system paths (e.g., SSH keys, environment files) were found. The scripts only read local project metadata.
[REMOTE_CODE_EXECUTION] (SAFE): There are no instances of remote script downloads or piped execution (e.g., curl | bash). All scripts are self-contained and perform static analysis.
[PROMPT_INJECTION] (SAFE): The markdown files are purely technical documentation and guides. They contain no instructions intended to override agent behavior or bypass safety filters.

kotlin-multiplatform