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
Risk Level
SAFE
Analyzed
Apr 25, 2026, 02:58 PM