build-house-from-plan
Warn
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: MEDIUMDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The script
scripts/render_house.pyincludes a functionload_film_scriptthat usesimportlib.utilto dynamically load and execute Python modules. The path to the script is retrieved from thescriptfield in the user-providedplan.jsonfile. This pattern allows for the execution of arbitrary local Python code if a malicious plan file is supplied. - [DYNAMIC_EXECUTION]: The script
scripts/fetch_assets.pyuses theexec()function to process a configuration line extracted from the localhouse_core.pyfile to determine the asset library path. - [EXTERNAL_DOWNLOADS]: The skill downloads 3D assets and metadata from external sources to populate the Blender scene.
scripts/fetch_assets.pyfetches textures and HDRI environment maps from Poly Haven and ambientCG.scripts/fetch_objaverse.pyandscripts/find_objaverse.pydownload 3D models and search metadata from the Objaverse dataset repository on Hugging Face.- [COMMAND_EXECUTION]: The skill instructions in
SKILL.mdrequire the execution of various shell commands viauv runandblenderto run the included Python scripts for plan validation, model building, and rendering. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes complex, untrusted
plan.jsonfiles and 2D drawing data. A malicious input could attempt to influence the agent's behavior or exploit scripts that utilize data from the plan (such as the dynamic script loading functionality).
Audit Metadata