The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: Provides an installation option using curl -fsSL https://get.x-cmd.com | sh, which executes a remote shell script from the vendor's domain.
[EXTERNAL_DOWNLOADS]: Fetches core binaries, tools, and package metadata from the vendor's GitHub repository (github.com/x-cmd/release) and established services like conda.prefix.dev.
[COMMAND_EXECUTION]: Instructs the agent to source a local initialization script (. ~/.x-cmd.root/X) to configure the shell environment and PATH.
[COMMAND_EXECUTION]: Uses a dedicated package manager (x env use or x pixi use) to download and execute various CLI tools and development environments.
[PROMPT_INJECTION]: The skill processes external tool outputs and reads from remote configuration files, which constitutes a surface for potential indirect prompt injection.
Ingestion points: Reads tool outputs and remote metadata from https://x-cmd.com/llms.txt in SKILL.md.
Boundary markers: None identified in the provided instructions.
Capability inventory: Subprocess calls for package installation (x env use, x pixi use) and shell execution across all scripts.
Sanitization: No explicit sanitization or validation of the remote content is described.

x-cmd