unity-csharp-edit
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill's functionality involves reading and processing C# source files, which presents an indirect prompt injection surface. * Ingestion points: Reads code from .cs files and symbol data using unity-cli and file system tools. * Boundary markers: No specific boundary markers or instructions are provided to the agent to distinguish between code and potential instructions in comments. * Capability inventory: The agent can write files, update project settings, and execute unity-cli commands. * Sanitization: No explicit content sanitization is performed on the code before the agent processes it.
- [COMMAND_EXECUTION]: The skill relies on executing the unity-cli binary and potentially building it from source using cargo run. These commands are standard for the intended developer use case and operate within the project context.
Audit Metadata