jgengine-gameplay
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill provides Chat and Dialogue primitives that process untrusted player data, establishing a surface for indirect prompt injection. | Ingestion points: createChat and createGameDialogue (api.md). | Boundary markers: Developers are provided with createChatFilter to implement boundaries. | Capability inventory: fetchJson (network) and createSaveStore (persistence) are available in the engine (api.md). | Sanitization: normalizeChatText and createChatFilter are included for data processing.
- [EXTERNAL_DOWNLOADS]: The framework includes utility functions for retrieving remote game data as part of its core functionality. | Evidence: fetchJson, createJsonDataSource, and proxiedUrl (api.md) allow the engine to fetch content from external URLs. These are recognized as legitimate vendor-owned resource patterns for the jgengine ecosystem.
Audit Metadata