The Agent Skills Directory

[SAFE]: The skill utilizes local search tools like grep and rg to perform project context detection. It inspects deployment targets in Package.swift and *.pbxproj files and searches for existing CloudKit or persistence layer code. These operations are limited to the local environment and are standard for a code-generation tool.
[SAFE]: The provided Swift templates implement secure coding practices. Specifically, the SyncEngine and RecordSystemFieldsEncoder classes use NSKeyedArchiver and NSKeyedUnarchiver with requiringSecureCoding enabled to handle data persistence securely.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting and processing untrusted data from the local project environment and user responses to generate code.
Ingestion points: Project configuration files (Package.swift, *.pbxproj, *.entitlements), Swift source files, and user input via AskUserQuestion (SKILL.md).
Boundary markers: None identified; the skill directly interpolates detected data into Swift templates.
Capability inventory: The skill has capabilities to read, write, and edit files, execute bash commands, and query the user.
Sanitization: There is no evidence of explicit validation or escaping for external content before it is processed by the agent to generate new source files.

cloudkit-sync