unity-netcode

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines tools that ingest user-provided parameters (such as class names, file paths, and network configurations), which creates an attack surface for instructions embedded in untrusted data.
  • Ingestion points: Tool parameters in SKILL.md for netcode_add_network_behaviour_script and netcode_configure_manager.
  • Boundary markers: Not explicitly defined in the instruction markdown.
  • Capability inventory: Includes file writing (script generation) and network configuration modification.
  • Sanitization: Not explicitly described in the markdown; relies on the underlying tool implementation.
  • [DYNAMIC_EXECUTION]: The netcode_add_network_behaviour_script tool generates C# source code files from templates, which triggers Unity's compilation and domain reload processes. This is the intended functionality for a developer scaffolding tool.
  • [COMMAND_EXECUTION]: The skill provides tools to control the Unity engine's runtime state (e.g., starting a host, server, or client via netcode_start_host), which involves executing networking logic within the Unity process environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 06:52 AM