blender-forge

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill drives external tools including Blender and FFmpeg to perform 3D rendering and video encoding.
  • Evidence: In scripts/encode_turntable.py, the run function uses subprocess.run() with command lists. This implementation is secure as it avoids the shell=True parameter, preventing command injection vulnerabilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill handles user-provided text for 3D inscriptions, which represents a potential injection surface.
  • Ingestion points: Untrusted data enters the context through arguments like --signs, --line, and --text in scripts/make_vessel.py and scripts/make_tablet.py.
  • Boundary markers: Instructions are logically separated by script arguments; however, no explicit prompt delimiters are used for the text content itself.
  • Capability inventory: The skill can write files (GLB, JSON, PNG) and execute local binaries (FFmpeg) via subprocess calls.
  • Sanitization: Includes input validation such as profile checks in scripts/make_vessel.py and Unicode glyph resolution in scripts/signs.py.
  • [EXTERNAL_DOWNLOADS]: Mentions external dependencies required for operation.
  • Evidence: SKILL.md identifies Blender and FFmpeg as requirements and suggests installation via Homebrew. These are well-known and trusted software packages.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 03:22 AM