The Agent Skills Directory

[COMMAND_EXECUTION]: The skill exposes capabilities to execute arbitrary shell commands and interact with terminal processes through functions like start_process and interact_with_process. These tools allow the agent to run scripts and system commands directly in environments such as PowerShell.
[INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by processing untrusted data.
Ingestion points: Untrusted data enters the context via read_file (reading workspace files), read_process_output (reading terminal output), and list_directory (reading file metadata).
Boundary markers: The instructions do not define delimiters or warnings to ignore instructions embedded in the processed data.
Capability inventory: The skill possesses significant capabilities including file writing (write_file), directory creation (create_directory), and arbitrary process execution (start_process).
Sanitization: There is no evidence of sanitization or filtering of external content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill references an external project repository on GitHub (wonderwhy-er/DesktopCommanderMCP) for tool documentation and implementation details.

mcp-desktop-commander