gamekit
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill content is educational and documentation-focused, providing Swift code samples for GameKit features. No malicious code, obfuscation, or unauthorized data access patterns were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill documentation correctly identifies the potential for indirect injection via multiplayer match data and provides mitigation guidance.
- Ingestion points: Data received from remote players via
GKMatchDelegateinSKILL.mdandGKTurnBasedEventListenerinreferences/gamekit-patterns.md. - Boundary markers: Not applicable to this documentation-style skill, which focuses on providing implementation code for the agent to follow.
- Capability inventory: The skill describes capabilities such as saving data to iCloud (
saveGameData) and submitting scores to leaderboards. - Sanitization: The skill explicitly warns to 'Treat received match data as untrusted input', which is a best-practice security recommendation for handling data from remote players.
Audit Metadata