The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill directs the agent to gather information from external resources and user-provided notes to generate lessons and components. This creates an attack surface where malicious instructions embedded in external sites could influence the agent's behavior.
Ingestion points: External websites/resources fetched to populate RESOURCES.md and generate lessons; user-provided content in MISSION.md, NOTES.md, and sequential learning records.
Boundary markers: The instructions lack specific guidance on using delimiters or system warnings to prevent the agent from following instructions found within the ingested data.
Capability inventory: The agent is authorized to write multiple files (./lessons/*.html, ./assets/*, and various markdown records) and is encouraged to execute CLI commands to open these files for the user.
Sanitization: There is no mention of sanitizing, escaping, or validating the content retrieved from external URLs before it is processed or incorporated into generated files.
[DYNAMIC_EXECUTION]: The skill requires the agent to generate and save executable web content, including HTML lessons and reusable JavaScript or CSS components, to the ./lessons/ and ./assets/ directories.
[COMMAND_EXECUTION]: The agent is instructed to open generated files using a CLI command, which represents a standard command execution interface for user convenience.

teach