unity-transactional-boosters
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a framework for processing external game state data that could potentially be influenced by untrusted sources.
- Ingestion points: The skill instructs the agent to inspect inventory IDs, save transactions, session states, and board predicates (SKILL.md).
- Boundary markers: There are no explicit instructions for using delimiters or boundary markers to isolate external game data from the agent's instructions.
- Capability inventory: The skill utilizes project management tools (unity-cli, unity-game-dev) and backend integration (firebase-game-backend).
- Sanitization: No explicit sanitization or validation steps are outlined for the ingested game state data.
Audit Metadata