The Agent Skills Directory

[COMMAND_EXECUTION]: The instructions in SKILL.md direct the agent to 'open the lesson file for the user by running a CLI command' such as a system opener to display generated HTML lessons.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process data from external, untrusted resources.
Ingestion points: External resources (books, articles, and communities) linked and managed in RESOURCES.md and user-supplied mission parameters.
Boundary markers: No specific boundary markers or 'ignore' instructions are provided to the agent for handling content from external sources.
Capability inventory: The skill performs file system operations (read/write) for workspace management and executes CLI commands to open files.
Sanitization: There are no instructions for sanitizing or validating external content before it is incorporated into lessons or learning records.

teach