gdscript-quality

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a bash script (scripts/check.sh) that headlessly invokes the Godot engine binary to perform static analysis on GDScript files. The script is designed for local execution within the Godot project directory and uses standard shell patterns for binary detection and path handling.
  • [INDIRECT_PROMPT_INJECTION]: As the skill is designed to read and refactor existing code files within a Godot project, it possesses an inherent surface for indirect prompt injection where malicious instructions embedded in project files could attempt to influence the agent's behavior.
  • Ingestion points: The agent reads .gd and project.godot files to perform its tasks.
  • Boundary markers: The skill instructions do not specify the use of delimiters or specific warnings when interpolating code content into the prompt.
  • Capability inventory: The skill has the ability to write to files (modifying project.godot) and execute shell commands (via check.sh).
  • Sanitization: There is no evidence of specific sanitization or filtering logic applied to the content of ingested files.
  • [SAFE]: The core functionality of the skill involves standard code quality checks and refactoring patterns. All file and system operations are scoped to the user's project environment and are consistent with the documented purpose of assisting in Godot development.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 02:36 AM