godot-voxel-tools

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a bundled maintenance script scripts/preflight.py to verify the integrity of local source files. The script is designed with security constraints, such as preventing symlink traversal and blocking access to sensitive configuration directories (e.g., .ssh, .aws, .env).
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze Godot project files and documentation. It mitigates risk by instructing the agent to never execute commands found within retrieved text and requiring explicit human approval for any state-changing actions.
  • [SAFE]: The skill follows security best practices by implementing an 'evidence-first' approach, gating all mutation operations (builds, installs, exports) behind explicit user approval, and providing a preflight check script that limits its own scope to non-sensitive files.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 08:52 AM