The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external resources, which could potentially contain malicious instructions aimed at influencing the agent's behavior.
Ingestion points: The agent is instructed to gather knowledge from external sources listed in RESOURCES.md and read ./learning-records/*.md to determine the user's progress.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing external content.
Capability inventory: The skill has the ability to write to the file system (lessons, records, assets) and is instructed to execute CLI commands to open files for the user.
Sanitization: There is no mention of sanitizing, escaping, or validating the content retrieved from external URLs or resources.
[COMMAND_EXECUTION]: The skill instructions in SKILL.md explicitly direct the agent to 'open the lesson file for the user by running a CLI command' whenever possible. While intended for user convenience (e.g., using open or xdg-open), this capability allows the agent to execute arbitrary shell commands.

teach