analyzing-query-performance

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is configured to use database CLI tools (psql, mysql, mongosh) via the allowed-tools frontmatter. These are used strictly for executing diagnostic queries and retrieving performance metrics as part of the skill's stated purpose.
  • [SAFE]: The instructions follow industry best practices for SQL performance tuning, such as identifying sequential scans, checking buffer cache hit ratios, and analyzing execution plans.
  • [SAFE]: All external resources and documentation links point to official database manuals or well-known, reputable technical resources for database administrators.
  • [SAFE]: An indirect prompt injection surface is present as the skill processes output from database execution plans. However, the risk is negligible as the agent focus is on quantitative performance data.
  • Ingestion points: Database query results and EXPLAIN plans in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: Database CLI tools (psql, mysql, mongosh) and file system tools (Read, Write, Edit, Grep, Glob) listed in SKILL.md.
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 09:30 PM