The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to "open the lesson file for the user by running a CLI command" after creation. This pattern, intended for user convenience, can be exploited if the command execution is not restricted to safe file-opening utilities.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process data from external sources and user-generated notes.
Ingestion points: RESOURCES.md, NOTES.md, and MISSION.md (via SKILL.md).
Boundary markers: None specified to differentiate between instructions and educational content.
Capability inventory: File system write access (./lessons/*.html, ./learning-records/*.md, etc.) and CLI command execution.
Sanitization: No mention of escaping or validating content retrieved from external resources.

teach