Skills
Navigate
skills/proyecto26/blender-ai-plugin/pixel-art-style/Gen Agent Trust Hub

pixel-art-style

Warn

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill utilizes runpy.run_path to execute Python scripts from relative paths constructed at runtime (e.g., f"{skills}/isometric-style/scripts/iso_camera.py"). This facilitates the dynamic loading and execution of code based on computed string paths.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data through the target variable, which is interpolated into script arguments and executed.
  • Ingestion points: The target variable defined in SKILL.md used for styling assets.
  • Boundary markers: No specific delimiters or safety instructions are provided to the agent regarding the interpolation of this variable.
  • Capability inventory: Multiple runpy.run_path calls that execute local Python scripts based on external inputs.
  • Sanitization: No sanitization or validation logic is present for the target input before it is passed to the script environment.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 30, 2026, 06:05 PM