managing-database-partitions

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill instructions utilize standard database administration commands such as CREATE TABLE, ALTER TABLE, and EXPLAIN to implement partitioning strategies. These operations are within the expected scope of the skill's stated purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface for indirect prompt injection as it processes external database data and metadata.
  • Ingestion points: Accesses database metadata via pg_stat_user_tables and sample data from assets/example_data.csv.
  • Boundary markers: The skill instructions in SKILL.md do not include explicit markers or instructions to ignore embedded commands within the processed data.
  • Capability inventory: The skill uses database shell tools including psql, mysql, and mongosh (defined in SKILL.md), and references automation scripts like partition_implementation.py (defined in scripts/README.md) which possess Write and Edit capabilities.
  • Sanitization: There are no documented procedures for sanitizing or validating data read from external database sources or CSV files before processing.
  • [EXTERNAL_DOWNLOADS]: The skill provides links to official PostgreSQL and MySQL documentation, as well as the well-known pg_partman extension on GitHub. These are established technical resources used for educational and reference purposes and are treated as safe sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:48 AM