game-ux
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes game codebase files which are untrusted external inputs that could contain malicious instructions.
- Ingestion points: Analyzes UI code, HUD implementations, menu systems, and engine-specific assets (Unity, Unreal, Godot) within the audited project.
- Boundary markers: The instructions lack explicit delimitation or warnings to ignore embedded commands within the analyzed data.
- Capability inventory: The skill has the ability to read files and execute arbitrary shell commands for building and testing.
- Sanitization: There is no evidence of filtering or validation of the content found within the audited files before it is processed by the agent context.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands defined within the target project's environment.
- Evidence: The 'SELF-HEALING VALIDATION' phase directs the agent to 'Run the project's test suite' and 'Run build/compile'. This permits the execution of arbitrary commands or scripts configured in the project's build system, which may be malicious if the project itself is untrusted.
Audit Metadata