The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/slice_model.py utilizes subprocess.run() to execute the bambu-studio CLI. The command is constructed using a list of arguments, which is a secure implementation that prevents shell injection attacks.
[EXTERNAL_DOWNLOADS]: The skill constructs and references search URLs for reputable 3D model hosting services, including Printables, MakerWorld, Thingiverse, and MyMiniFactory. These are well-known services and the interaction is limited to standard search query parameters.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external websites which could potentially contain adversarial content intended to influence the agent.
Ingestion points: scripts/search_models.py returns model names, URLs, and descriptions from external 3D model repositories to the agent.
Boundary markers: No specific delimiters or "ignore" instructions are used when displaying the external metadata to the agent.
Capability inventory: The skill possesses file writing capabilities and command execution via the bambu-studio utility in scripts/slice_model.py.
Sanitization: The skill employs urllib.parse.quote to sanitize search queries sent to repositories, but it does not filter or sanitize the content retrieved from those repositories for potential prompt injection markers.

bambu-print