The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes data from both local and remote sources, creating a surface for indirect prompt injection.\n
Ingestion points: Reads the local LEARNING.md file and fetches lesson content (en.md, quiz.json, README.md) from a remote GitHub repository.\n
Boundary markers: The instructions in SKILL.md do not include explicit delimiters or warnings to ignore embedded instructions within the lesson materials.\n
Capability inventory: According to SKILL.md, the agent has the capability to update the local LEARNING.md file and execute code snippets extracted from the curriculum content.\n
Sanitization: There is no description of sanitization or validation of the fetched remote content before it is processed or executed.\n- [REMOTE_CODE_EXECUTION]: The skill involves the execution of code snippets found within the curriculum files fetched from the remote GitHub repository. While this is a core part of the 'AI Engineering' lessons, it involves running content retrieved from a remote source.\n- [EXTERNAL_DOWNLOADS]: The skill fetches lesson data and quizzes from the author's GitHub repository at https://raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/. This is the primary method for delivering curriculum content to the agent.

learn