The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions suggest that the agent should open lesson files for the user by running a CLI command. This is a functional feature for the user experience but constitutes a direct instruction for command execution based on generated file paths.
[INDIRECT_PROMPT_INJECTION]: The skill's primary workflow involves fetching and processing information from external sources to populate the teaching workspace, creating a vulnerability surface where malicious instructions in external content could influence the agent's behavior.
Ingestion points: The agent reads from RESOURCES.md, which contains external links and annotations, as well as MISSION.md and NOTES.md which contain user-supplied context.
Boundary markers: There are no instructions provided to the agent to treat external content as untrusted or to use delimiters to separate source material from its own instructions.
Capability inventory: The agent has the capability to write various file types to the local filesystem (Markdown, HTML, CSS, JS) and to execute CLI commands to open these files.
Sanitization: The instructions do not specify any validation, filtering, or escaping mechanisms for data retrieved from the RESOURCES.md links before it is used to generate lessons or interactive simulators.

teach