musickit
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill references non-existent software versions, specifically Swift 6.3 and iOS 26+. While likely intended as a futuristic placeholder or stylistic choice by the author, this deceptive metadata could cause an AI agent to misjudge platform capabilities or generate code for hypothetical environments that do not currently exist.\n- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates processing and displaying dynamic content fetched from the Apple Music catalog, which is an external and untrusted data source.\n
- Ingestion points: Track metadata and search results fetched via MusicCatalogSearchRequest in SKILL.md and displayed in MusicSearchView in references/musickit-patterns.md.\n
- Boundary markers: The provided code and instructions lack explicit delimiters or instructions to ignore potential commands embedded within song titles or artist names.\n
- Capability inventory: The skill is limited to media playback control, library management, and UI rendering; it does not expose dangerous capabilities such as shell execution or unauthorized network exfiltration.\n
- Sanitization: The skill relies on standard SwiftUI rendering components but does not implement specific sanitization to prevent the AI from interpreting instructions embedded in fetched metadata.
Audit Metadata