The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety filters, or extract system prompts were detected in the skill instructions or metadata.
[DATA_EXFILTRATION]: The skill does not contain any network operations targeting external domains. Code examples for loading images utilize the standard Blender API (bpy.data.images.load) with local path placeholders, which is typical for addon development.
[REMOTE_CODE_EXECUTION]: No remote code downloads (e.g., via curl or wget) or dynamic execution patterns (such as eval or exec) were found in any of the provided files.
[COMMAND_EXECUTION]: There are no shell command execution patterns or uses of subprocess modules. The skill focuses entirely on internal Blender Python API operations.
[CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or private tokens were identified. Guidelines suggest standard local file paths for assets.
[SAFE]: All external documentation links point to the official docs.blender.org domain, which is a well-known and trusted resource for the Blender community.

blender-core-gpu