The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from textbook chapters (docs/chapters//index.md) and glossaries to generate quiz questions. This data ingestion creates a surface for indirect prompt injection, where instructions embedded in the processed text could potentially influence the agent's logic. Ingestion points: docs/chapters//index.md, docs/glossary.md, and docs/course-description.md. Boundary markers: No explicit delimiters or warnings are used to differentiate untrusted chapter content from system instructions. Capability inventory: The skill has permissions to write markdown/JSON files and modify the project's mkdocs.yml configuration. Sanitization: The skill lacks explicit sanitization or filtering of the external chapter text before it is used in the quiz generation prompt.
[COMMAND_EXECUTION]: The skill executes local shell commands to track time and generate session logs. Evidence: Uses the date command in SKILL.md to record the start and end times of the quiz generation process.

quiz-generator