blender-community-skill-bootstrap

Fail

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill directs the agent to download and install executable agent skills from a non-vendor GitHub repository (RobLe3/cc-blender-skill).
  • The installation workflow utilizes a helper script install-skill-from-github.py to fetch and integrate external code into the agent's workspace.
  • Although the instructions specify a pinned commit hash (11016c9a5847897491dde935c346571bd7548e3d), the source repository belongs to an unverified individual account rather than a recognized trusted organization.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes an ingestion pipeline for external instructions that could be leveraged for indirect prompt injection attacks.
  • Ingestion points: Remote skills are pulled from the RobLe3/cc-blender-skill repository as defined in SKILL.md.
  • Boundary markers: The instructions mandate that the agent informs the user of the repository source, specific revision, and license before proceeding with installation.
  • Capability inventory: The installed components (e.g., text-to-blender, blender-modeling, blender-animation listed in SKILL.md) grant the agent extensive control over 3D modeling environments and file export operations.
  • Sanitization: The workflow includes a post-installation validation step using a quick_validate.py script from the $skill-creator tool to check the integrity of the downloaded folders.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Aug 22, 2026, 06:06 PM
Security Audit — agent-trust-hub — blender-community-skill-bootstrap