The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a Python script (scripts/main.py) to process text and generate flashcards. The execution is localized to the agent's environment and uses the standard library (argparse, re) without spawning dangerous subprocesses or utilizing unsafe functions like eval() or exec().
[DATA_EXPOSURE]: The script reads from user-specified input files and writes to a local output file (default anki_cards.txt). There is no evidence of data exfiltration or access to sensitive system paths like .ssh or .aws credentials.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns were detected. The skill does not use curl | bash or similar patterns, and all logic is contained within the provided scripts.
[EXTERNAL_DOWNLOADS]: While the documentation mentions capabilities like "Auto-download and embed relevant images," the provided implementation (scripts/main.py) does not contain networking code (no requests, urllib, etc.). The actual code provided is strictly for text parsing and TSV generation.
[PROMPT_INJECTION]: The SKILL.md file contains standard instructional content for a medical study tool. It does not attempt to override safety filters or bypass system instructions.

anki-card-creator