The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses tools such as tar, rsync, and the aws CLI for its operations. These tools are restricted by prefix in the allowed-tools configuration to their specific backup-related subcommands.\n- [DATA_EXFILTRATION]: The skill is designed to transfer data to external destinations (e.g., AWS S3, remote NAS). While this is the intended function, it involves moving potentially sensitive information like database dumps and configuration files off-site.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection.\n
Ingestion points: Data from file systems (via rsync/tar) and database contents (via pg_dump/mysqldump) read during backup tasks in SKILL.md.\n
Boundary markers: Absent. The instructions do not specify how to handle or ignore instructions embedded in the data being backed up.\n
Capability inventory: Subprocess execution via Bash (including tar, rsync, and aws), and file system modification via Write and Edit tools.\n
Sanitization: Absent. There are no steps to validate or sanitize data content before processing.\n- [NO_CODE]: Several scripts listed in the scripts/README.md file, including backup_database.sh, restore_database.sh, validate_backup.py, and configure_backup_agent.py, are referenced but their source code is not included in the skill package.

implementing-backup-strategies