database-agent
Security checks across static analysis, malware telemetry, and agentic risk
Overview
The skill's code, instructions, and resource files are consistent with its stated database-assistant purpose (slow-SQL analysis, schema checks, safe corrections, and test-data generation), but it will require you to supply database credentials/config and can execute SQL — review and run carefully in non-production with least-privileged credentials.
This skill is coherent for database maintenance tasks, but it performs operations that can modify data. Before installing or running it: (1) review the scripts (especially validate_data_correction.py and any execution paths) to confirm they require explicit confirmation and produce rollback scripts; (2) always provide a least-privileged test account (not root) and prefer a staging database; (3) inspect generated SQL before executing and run generated scripts in non-production first; (4) keep backups and audit logs, and enforce the >1000-row confirmation policy mentioned in SKILL.md; (5) if you will supply credentials as a JSON config file, store that file securely and avoid sharing production credentials with the skill unless you accept the risk. If you want higher assurance, ask for full content of the truncated scripts (analyze_slow_sql.py, validate_data_correction.py, generate_report.py, check_schema_compliance.py) so those can be reviewed for any unexpected behavior (network calls, hidden logging, or filesystem exfiltration).
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
No visible risk-analysis findings were reported for this release.