The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads from local workspace files to inform its teaching logic, which creates a potential surface for instructions within those files to influence the agent's behavior during content generation.
Ingestion points: The agent is instructed to read MISSION.md and existing learning records in the learning-records/ directory as part of Step 2.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' commands when processing the content of these files.
Capability inventory: The agent has the ability to write new files to the filesystem, including HTML, JavaScript, and Markdown files.
Sanitization: There are no instructions provided to sanitize or filter the data retrieved from the workspace files before it is interpolated into generating lessons.
[DYNAMIC_EXECUTION]: The skill involves the runtime generation of interactive content that includes executable scripts.
Evidence: Step 4 instructs the agent to "Generate a reusable, interactive diagnostic widget stored in the configured assets/ directory and embed it into the lesson HTML." This involves generating JavaScript code that handles validation and randomized logic.

teachme