The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze, review, and build SwiftUI component architectures based on external code or descriptions provided in the workspace. This ingestion of untrusted data represents a potential attack surface. The skill lacks explicit boundary markers (delimiters) or sanitization instructions to distinguish between its core logic and instructions that might be embedded within the processed Swift code. However, the risk is mitigated by the specific, restricted architectural patterns the agent is instructed to follow.

swiftui-style-driven-components