urp-postprocessing

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill leverages the unity command eval tool to execute dynamically generated C# statement blocks in a connected Unity Editor. This allows for runtime modification of Volume profiles, camera settings, and asset creation, which is a powerful capability restricted to the local development environment.\n- [COMMAND_EXECUTION]: The instructions involve invoking the unity-cli tool to interact with the Unity Editor's command catalog and execute C# snippets via the eval command, representing direct command-line interaction with the host system's development tools.\n- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates an attack surface for indirect prompt injection by searching for and operating on scene objects (e.g., GameObject.Find). If the agent is instructed to use user-defined object names from an untrusted scene in the C# snippets it generates, malicious names could potentially be used to influence the code logic, although the current implementation uses hardcoded defaults for common tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 12:38 PM