The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the uvx tool runner to install and execute the albumentationsx-mcp package. This is the standard procedure for deploying Model Context Protocol (MCP) servers on a host system.- [EXTERNAL_DOWNLOADS]: Fetches the albumentationsx-mcp package from the Python Package Index (PyPI). The package name is consistent with the stated purpose of the skill and the author's infrastructure.- [SAFE]: The skill implements a 'least privilege' approach by requiring the use of --allowed-root and --artifact-root flags. This ensures that the agent's file system access is restricted to specific, user-defined directories.- [SAFE]: Included safety guidelines explicitly prohibit high-risk operations such as fetching remote images, overwriting original datasets, or training models, which reduces the attack surface for data exfiltration and indirect prompt injection.

albumentationsx-mcp