cost-report

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs analytical tasks on Snowflake metadata using a set of provided financial operations (FinOps) and SQL tools.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill retrieves and processes query text from Snowflake's QUERY_HISTORY table in SKILL.md.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present when analyzing external query strings.
  • Capability inventory: Uses analytical tools like sql_analyze and finops_warehouse_advice which operate on the retrieved data.
  • Sanitization: No explicit sanitization or filtering is performed on the query text before it is presented for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 04:45 AM
Security Audit — agent-trust-hub — cost-report