game-qa
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data from game projects and runtimes, creating a potential vector for indirect prompt injection.
- Ingestion points: The skill reads project-specific scripts, test configurations, engine conventions, runtime errors, and failed asset load logs (referenced in SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the ingested content are defined.
- Capability inventory: The skill utilizes tool-based capabilities such as
game_usefor interacting with web previews, established build/logic checks, and engine-specific connections for interaction and state inspection. - Sanitization: There is no evidence of sanitization, escaping, or validation logic for the external content before it is processed by the agent.
Audit Metadata