The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of local Python scripts (memento_cards.py and youtube_quiz.py) to manage flashcard data, calculate statistics, and fetch external content.
[EXTERNAL_DOWNLOADS]: The instructions direct the agent to advise the user to install an external dependency, youtube-transcript-api, via pip if it is not already present.
[INDIRECT_PROMPT_INJECTION]: The skill fetches video transcripts from YouTube and processes them to generate quiz questions. If a transcript contains malicious instructions, they could potentially influence the agent's behavior during the generation process.
Ingestion points: Transcript text fetched from YouTube via the youtube_quiz.py script.
Boundary markers: Absent. The instructions do not define specific delimiters or isolation techniques for the transcript content when it is provided to the LLM for processing.
Capability inventory: The skill can add, delete, and export flashcards using the memento_cards.py script.
Sanitization: The skill does not perform any sanitization or filtering of the transcript content before it is processed.
[DATA_EXFILTRATION]: The skill accesses and writes to files in the user's home directory, specifically under ~/.hermes for application data and user-defined paths for CSV export operations.

memento-flashcards