documentdb-query-optimizer

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a secure workflow for database administration, including mandatory user approval for index modifications and the use of scoped tools for diagnostic data collection.
  • [EXTERNAL_DOWNLOADS]: References core indexing principles and best practices from official Microsoft Azure documentation (learn.microsoft.com).
  • [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection via the ingestion of database content.
  • Ingestion points: Fetches sample documents using find_documents and analyzes query plans via optimize_find_query in SKILL.md.
  • Boundary markers: Absent; the instructions do not implement specific delimiters for untrusted database data.
  • Capability inventory: Limited to database indexing tools (create_index, drop_index) which require explicit user confirmation.
  • Sanitization: No explicit sanitization of database values is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 09:28 PM
Security Audit — agent-trust-hub — documentdb-query-optimizer