snowflake-development

Pass

Audited by Gen Agent Trust Hub on Nov 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted SQL input for optimization and sizing analysis, which constitutes a potential surface for indirect prompt injection if the input files contain malicious instructions.\n
  • Ingestion points: The script scripts/snowflake_query_helper.py reads SQL content from files specified by the --file flag or strings passed via --sql.\n
  • Boundary markers: The script does not use specific delimiters or instructions to the agent to ignore embedded content within the SQL text.\n
  • Capability inventory: The skill is limited to performing static analysis via regular expressions and calculating warehouse sizes; it does not possess network capabilities, file-writing permissions, or the ability to execute shell commands beyond its own script.\n
  • Sanitization: No sanitization or filtering is performed on the ingested SQL text before it is analyzed.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 8, 2026, 03:14 PM