The Agent Skills Directory

[SAFE]: The skill is a pedagogical tool that operates entirely within the expected boundaries of a code-analysis and quizzing utility. It uses local markdown templates for its logic and does not include any executable scripts, binary files, or external network requests.
[INDIRECT_PROMPT_INJECTION]: The skill inherently processes untrusted data as it reads source code and documentation from the local environment to generate quiz content.
Ingestion points: The agent reads source files, intent documents, and test files as part of its 'Prepare and conduct' phase in SKILL.md.
Boundary markers: There are no explicit instructions to the agent to treat file content as data only or to ignore potential instructions embedded in comments or documentation.
Capability inventory: The skill's operations are limited to reading files and outputting text to the user; it lacks the ability to write files, execute shell commands, or perform network operations.
Sanitization: The skill does not perform sanitization on the code content it reads.
Risk Assessment: Given that the ingestion is required for the skill's primary purpose and the agent's capabilities are restricted, this surface is considered low-risk and acceptable for the intended use case.

quiz-codebase