blender-creation

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on shell command execution for its primary functions. scripts/asset_build_utils.py uses subprocess.run to invoke the Blender binary for rendering and diagnostics. SKILL.md instructs the agent to use uv run to execute various processing and verification scripts.
  • [PRIVILEGE_ESCALATION]: The instructions in SKILL.md include a routine to check for the Blender binary and execute sudo apt-get update && sudo apt-get install -y blender if it is missing, requiring administrative privileges for software installation.
  • [EXTERNAL_DOWNLOADS]: The skill performs network operations to fetch external resources. scripts/asset_build_utils.py uses urllib.request.urlopen to download PBR texture maps from ambientcg.com (a well-known asset repository). Additionally, SKILL.md directs the agent to download reference images from user-provided URLs using curl.
  • [DYNAMIC_EXECUTION]: The modeling pipeline involves generating Python scripts at runtime (e.g., build_asset.py, verify_and_render.py) which are then executed within the Blender environment or via uv. This is a standard mechanism for programmatic 3D content creation but constitutes dynamic code generation.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from product URLs using a browser subagent to extract descriptive metadata. This represents an attack surface where malicious instructions embedded in external web content could potentially influence agent behavior during the modeling process.
  • Ingestion points: External product pages accessed via the browser subagent as specified in SKILL.md (§1.1).
  • Boundary markers: Not explicitly defined in the instructions for webpage content processing.
  • Capability inventory: File system access, shell command execution (subprocess.run), and network requests (urllib.request.urlopen).
  • Sanitization: No specific sanitization or escaping logic is described for the extracted metadata prior to its use in generating modeling parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 03:07 AM