geometry-nodes-for-ovrtx
Warn
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The instructions direct the agent to generate and execute Python code using the
blender-python-executiontool and run the localscripts/audit_geometry_nodes.pyscript within the Blender environment. - [REMOTE_CODE_EXECUTION]: The skill instructs the agent to use
blender-community-skill-bootstrapto 'obtain' theblender-modelinghelper library if it is not already installed. This constitutes a reference to an external and unverifiable source for executable code. - [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection via the
scripts/audit_geometry_nodes.pyscript. -- Ingestion points: The script reads object names from theGN_AUDIT_REQUESTglobal variable or command-line arguments. -- Boundary markers: No delimiters or instructions are used to separate user data from instructions. -- Capability inventory: The script operates within the BlenderbpyAPI, providing access to evaluation and scene data. -- Sanitization: Validation is limited to checking if objects exist and are of the 'MESH' type.
Audit Metadata