comparing-database-schemas

Warn

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/generate_migration_script.py generates bash scripts from input content and programmatically grants them executable permissions.
  • Evidence: The generate_script method in scripts/generate_migration_script.py writes a shell script and calls file_path.chmod(0o755).
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted database schemas and configuration files to generate executable scripts.
  • Ingestion points: External content passed to args.content and args.config in scripts/generate_migration_script.py, and files scanned in scripts/rollback_migration.py.
  • Boundary markers: The skill instructions do not specify any delimiters or safety warnings for handling embedded instructions in the processed data.
  • Capability inventory: The skill is authorized to use Bash(psql:*), Bash(mysql:*), and Bash(mongosh:*) tools, along with file system write and chmod capabilities.
  • Sanitization: No sanitization or validation logic is present to filter malicious commands or instructions from the source data before script generation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 12, 2026, 01:36 AM