The Agent Skills Directory

[SAFE]: The skill implements standard functionality for Blender preset management using established vendor libraries (dcc_mcp_core, dcc_mcp_blender). No malicious patterns such as prompt injection, obfuscation, or unauthorized data exfiltration were detected.
[INDIRECT_PROMPT_INJECTION]: The skill interacts with external data by reading and writing export presets to Blender scene metadata.
Ingestion points: Reads named presets from scene custom properties via list_export_presets and load_export_preset.
Boundary markers: Not explicitly defined in the provided scripts; logic is encapsulated within the vendor's interchange operations library.
Capability inventory: The skill has the capability to modify scene metadata (scene_metadata) but does not have access to shell execution, network operations, or dynamic code evaluation.
Sanitization: Preset names and options are passed to vendor-specific operations that handle the underlying Blender API calls.

blender-export-preset