The Agent Skills Directory

[NO_CODE]: The skill consists entirely of routing instructions and stop conditions for an AI agent. It contains no scripts, binaries, or executable commands.
[DATA_EXFILTRATION]: There are no network operations, credential exposures, or attempts to access sensitive file paths (such as .ssh, .aws, or .env files).
[PROMPT_INJECTION]: The instructions are focused on defining the scope of the SwiftData domain. There are no attempts to override system safety filters or bypass agent instructions.
[OBFUSCATION]: No obfuscation techniques such as Base64 encoding, zero-width characters, or homoglyphs were detected in the text or metadata.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute external scripts, nor does it define any package dependencies (npm, pip, etc.).
[DYNAMIC_CONTEXT_INJECTION]: The skill does not utilize dynamic shell execution placeholders (!command).

swiftdata