backup-restore-runbook-generator

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The provided script templates interpolate shell arguments (e.g., $BACKUP_FILE, $TARGET_TIME, $DB) directly into command lines and configuration files without explicit sanitization logic. * Ingestion points: Positional arguments in restore-postgres.sh, pitr-restore.sh, and validate-restore.sh in SKILL.md. * Boundary markers: None identified. * Capability inventory: Subprocess calls to aws, psql, pg_dump, mysqldump, systemctl, curl, and file system utilities. * Sanitization: No input validation or escaping is implemented.
  • [COMMAND_EXECUTION]: The skill generates scripts that execute powerful system and database management tools, including pg_dump, pg_restore, mysqldump, aws s3 CLI, and systemctl for service management. These operations are core to the skill's stated utility.
  • [DYNAMIC_EXECUTION]: The skill dynamically generates database recovery configuration files (e.g., recovery.conf) and executes database queries based on runtime arguments to validate data integrity.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:30 AM
Security Audit — agent-trust-hub — backup-restore-runbook-generator