game-ui-hud-and-diegetic-interfaces
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest external data including game states, content, platform rules, and approved visual systems to design interface surfaces. This creates a surface where malicious instructions embedded in game content or metadata could theoretically influence the agent's output.
- Ingestion points: The agent is instructed to read
game states,content,platform/input rules,approved visual systems, and performPrototype/build inspectionas defined inSKILL.md. - Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within the processed data.
- Capability inventory: The agent's capabilities are scoped to reading data and editing authorized design artefacts. The capability contract in
SKILL.mdexplicitly restricts the agent from performing implementation, participant contact, external SDK configuration, publication, or production changes without separate authority. - Sanitization: The instructions do not specify any sanitization, escaping, or filtering for the external content before it is processed.
- [NO_CODE]: The skill consists entirely of markdown documentation and design specifications without any accompanying scripts, executables, or configuration files that would perform automated actions.
Audit Metadata