sql-query-builder

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via processed data.
  • Ingestion points: Project data and parameters provided by the user in CSV, Excel, or JSON formats.
  • Boundary markers: None; the skill does not use delimiters to isolate untrusted data.
  • Capability inventory: The skill is limited to generating SQL strings and does not include capabilities for query execution or filesystem/network operations in the Python code.
  • Sanitization: The formatting logic in SKILL.md does not properly escape single quotes or other SQL control characters, making the generated queries potentially unsafe.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:28 AM