game-tutorial
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze untrusted data from game project environments, including source code, engine configurations, and string catalogs. This creates an attack surface where instructions embedded in the project files could influence the agent's behavior.
- Ingestion points: Step 1 and 2 instructions direct the agent to identify the engine, entry flow, input-binding system, and source code of the project.
- Boundary markers: The instructions do not specify the use of boundary markers or explicit prompts to ignore embedded instructions within the ingested project data.
- Capability inventory: The agent is instructed to modify the project (Step 4) and verify behavior by testing paths (Step 5), which may involve script execution or runtime interaction.
- Sanitization: There are no instructions for sanitizing or validating content retrieved from the game project files before processing.
Audit Metadata