godot-tdd-full

Warn

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent or user to download the Godot Unit Test (GUT) plugin via git clone https://github.com/bitwes/Gut.git. This repository belongs to a personal GitHub account and is not part of the trusted vendors or organizations list.
  • [REMOTE_CODE_EXECUTION]: The downloaded plugin is executed directly using the Godot binary with the command godot --path <project> -s addons/gut/gut_cmdln.gd. This pattern allows the execution of external scripts on the local system.
  • [COMMAND_EXECUTION]: The skill facilitates the use of various command-line tools including gdlint, gdformat, and godot to perform linting, formatting, and test execution. These commands operate with the permissions of the agent and can interact with the local file system.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it reads and processes external project files. Ingestion points: Reads content from design documents (e.g., design.md, test_cases.md) and GDScript files within the provided project path. Boundary markers: There are no explicit delimiters or instructions provided to separate untrusted file content from the agent's logic. Capability inventory: The skill can execute shell commands and write files to the system. Sanitization: There is no evidence of content sanitization or validation performed on the ingested project data before it is used in the TDD loop.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 12:46 AM