finding-expensive-queries

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious behaviors such as credential exfiltration, remote code execution, or obfuscation were detected. The SQL queries target standard Snowflake performance views.
  • [Indirect Prompt Injection] (LOW): The skill processes query_text from Snowflake logs, which could theoretically contain instructions intended to influence the agent. 1. Ingestion points: query_text field from SNOWFLAKE.ACCOUNT_USAGE.QUERY_HISTORY (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: SQL execution; no direct shell or network access. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:34 PM