The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses subprocess.run in scripts/list_books_json.py to execute the calibredb binary. The implementation uses a list-based command structure rather than a shell string, which effectively prevents shell injection vulnerabilities. The AST flag for shell=True was a false positive as the code correctly defaults to shell=False.
[CREDENTIALS_SAFE]: The documentation in SKILL.md explicitly warns against using literal passwords in shell arguments to prevent exposure in process lists. It correctly recommends using piped input or credential files with restricted permissions (0600), demonstrating a commitment to secure credential management.
[SAFE]: The command patterns provided in the reference files focus on standard library management tasks (listing, searching, metadata updates). Destructive actions like library restoration or book removal are correctly categorized as high-risk with instructions to seek user confirmation and perform backups beforehand.

calibredb