postgres-pro

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The scripts/backup_pg.py script executes administrative utilities such as pg_dump, psql, and pg_restore via subprocess.run. Furthermore, the documentation (EXAMPLES.md, REFERENCE.md) provides instructions for high-privilege operations using sudo to manage services and the file system.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way user-provided data is handled in administrative tasks.
  • Ingestion points: Database names and connection parameters ingested by scripts/backup_pg.py.
  • Boundary markers: No delimiters or instructions are used to isolate user-provided strings from system commands.
  • Capability inventory: The skill has capabilities including shell command execution and file system access for backups.
  • Sanitization: The _create_database method in scripts/backup_pg.py uses direct string interpolation to build SQL commands, lacking input validation or escaping for the database variable.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 08:31 AM
Security Audit — agent-trust-hub — postgres-pro