hz-unity-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation instructs the agent to use
npx -y metavrto run validation and performance monitoring tools. This pattern involves downloading and executing a package from the npm registry at runtime. - [COMMAND_EXECUTION]: The skill configuration explicitly allows and provides instructions for executing shell commands via
Bash(metavr:*)andBash(hzdb:*). These tools are intended for device management, app installation, and performance profiling on Meta Quest hardware. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted user data in the form of Unity C# scripts and project settings. This creates an attack surface where instructions embedded in code comments or strings could potentially manipulate the agent's logic.
- Ingestion points: The skill reads user-provided Unity source code and configuration files during the review process.
- Boundary markers: No specific delimiters or "ignore instructions" warnings are implemented to separate the data being reviewed from the skill's own operational instructions.
- Capability inventory: The agent has the ability to read project files and execute system commands via the allowed bash tools.
- Sanitization: The instructions do not specify any validation or sanitization steps for the code content before analysis.
Audit Metadata