The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the use of the mdplane CLI tool to perform operations on a host system, including file manipulation (read, cat, write, rm), directory management (mkdir, ls), and workspace administrative tasks (init, login, claim, export).
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through its ability to ingest data from external files and workspace search results.
Ingestion points: Commands such as mdplane read, mdplane cat, and mdplane search pull content from the workspace into the agent's context (identified in SKILL.md and references/command-surface.md).
Boundary markers: There are no instructions defining specific delimiters or safety warnings to prevent the agent from following instructions embedded within the processed file content.
Capability inventory: The skill provides significant system capabilities, including file system mutations and network-based workspace interactions.
Sanitization: No explicit sanitization or validation logic is provided for content retrieved via CLI commands before it is processed by the agent.

mdplane-cli