tvos-design
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions as an instructional layer for the agent when responding to user-provided tasks regarding tvOS development. This constitutes a potential surface for indirect prompt injection, as the agent may process untrusted user descriptions of apps or UI requirements.
- Ingestion points: Processes user queries and tasks involving tvOS, Apple TV, and 10-foot UI design.
- Boundary markers: No specific delimiters or "ignore instructions" warnings are utilized to wrap user-provided context.
- Capability inventory: The skill identifies no active capabilities; it does not execute shell commands, perform network operations, or write to the file system.
- Sanitization: There is no logic present for sanitizing or validating user input before processing.
- [NO_CODE]: The skill is comprised solely of markdown documentation, YAML frontmatter, and illustrative Swift/SwiftUI code snippets. It includes no Python scripts, Node.js modules, or shell scripts, which drastically limits the technical attack surface.
Audit Metadata