NYC

database-migrations-sql-migrations

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • PROMPT_INJECTION (LOW): The skill possesses an indirect prompt injection surface as it ingests user-provided $ARGUMENTS without explicit boundary markers to separate data from instructions. * Ingestion point: $ARGUMENTS; * Boundary markers: Absent; * Capability inventory: Bash, Write, Edit, Read; * Sanitization: Absent.
  • COMMAND_EXECUTION (LOW): The skill enables the 'Bash' tool to perform migration tasks. While legitimate for its primary purpose, this tool provides a high-privilege capability that could be exploited if malicious instructions are successfully injected into the agent's context through user-defined requirements.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:32 PM